@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/deepinfra.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":null,"catalog_only":true,"config_schema":null,"doc":"https://deepinfra.com/models","env":["DEEPINFRA_API_KEY"],"exclude_models":null,"extra":null,"id":"deepinfra","models":{"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.15,"output":1.15},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2025-06","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":917214,"hf_likes":1236,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","llmfit":{"architecture":"minimax_m3_vl","context_length":1048576,"discovered":false,"gguf_sources":[],"hf_downloads":164790,"hf_likes":1418,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M3","memory":{"min_ram_gb":238.6,"min_vram_gb":218.7,"recommended_ram_gb":397.7},"model_id":"MiniMaxAI/MiniMax-M3","moe":{"active_experts":4,"active_parameters":10000000000,"is_moe":true,"num_experts":128},"parameter_count":"427.0B","parameters_raw":427040140160,"pipeline_tag":"image-text-to-text","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-06-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":524288,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.3,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":66536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct Turbo","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"Qwen/Qwen3-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Instruct-GGUF"}],"hf_downloads":285987,"hf_likes":1042,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B Instruct","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"Qwen/Qwen3.5-122B-A10B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2114418,"hf_likes":603,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":2.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2666483,"hf_likes":1023,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-27B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.14,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2582188,"hf_likes":1480,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":"2025-01","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 35B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"input":0.45,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":416324,"hf_likes":1546,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":"2025-01","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 397B A17B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.5-9B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":12236962,"hf_likes":1781,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.32,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.95},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"Qwen/Qwen3.7-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.7-Max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"Qwen/Qwen3.8-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.206,"input":1.65,"output":4.951},"deprecated":false,"extra":{"attachment":true,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.8-Max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":359231,"hf_likes":383,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5","memory":{"min_ram_gb":173.7,"min_vram_gb":159.2,"recommended_ram_gb":289.4},"model_id":"XiaomiMiMo/MiMo-V2.5","moe":{"active_experts":8,"active_parameters":24764886000,"is_moe":true,"num_experts":256},"parameter_count":"310.8B","parameters_raw":310775040000,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/MiMo-V2.5-Pro-GGUF"}],"hf_downloads":53020,"hf_likes":727,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","memory":{"min_ram_gb":571.8,"min_vram_gb":524.1,"recommended_ram_gb":953.0},"model_id":"XiaomiMiMo/MiMo-V2.5-Pro","moe":{"active_experts":8,"active_parameters":71413954340,"is_moe":true,"num_experts":384},"parameter_count":"1023.2B","parameters_raw":1023244718976,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5-Pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.35,"input":0.5,"output":2.15},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":206900,"hf_likes":2457,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1-0528","knowledge":"2024-07","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1-0528","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":0.26,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1238427,"hf_likes":1462,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":"2024-12","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":163840,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.018,"input":0.09,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.018,"input":0.09,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1.3,"output":2.6},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.38},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-E4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-E4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemma 4 E4B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.32},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","knowledge":null,"last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Turbo","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":117872,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.1},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","moe":{"active_experts":1,"active_parameters":43930451431,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401649841664,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B FP8","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/Llama-4-Scout-17B-16E-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF"}],"hf_downloads":483763,"hf_likes":1331,"matched_hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","memory":{"min_ram_gb":60.7,"min_vram_gb":55.6,"recommended_ram_gb":101.2},"model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","moe":{"active_experts":1,"active_parameters":17000000000,"is_moe":true,"num_experts":16},"parameter_count":"108.6B","parameters_raw":108641793536,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","release_date":"2025-04-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":327680,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-01","last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.75,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2024-04","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.74,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.27,"input":2.7,"output":13.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","knowledge":null,"last_updated":"2025-07-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 Nemotron Super 49B v1.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-30B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-30B-A3B","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni 30B A3B Reasoning","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.037,"output":0.17},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.03,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"stepfun-ai/Step-3.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","llmfit":{"architecture":"step3p7","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Step-3.7-Flash-GGUF"},{"provider":"bartowski","repo":"bartowski/Step-3.7-Flash-GGUF"}],"hf_downloads":143509,"hf_likes":0,"matched_hugging_face_id":"stepfun-ai/Step-3.7-Flash","memory":{"min_ram_gb":112.5,"min_vram_gb":103.1,"recommended_ram_gb":187.5},"model_id":"stepfun-ai/Step-3.7-Flash","parameter_count":"201.4B","parameters_raw":201365316160,"pipeline_tag":"image-text-to-text","provider":"stepfun-ai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"stepfun-ai/Step-3.7-Flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"tencent/Hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":23137,"hf_likes":0,"matched_hugging_face_id":"tencent/Hy3","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"tencent/Hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":65012,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling","memory":{"min_ram_gb":532.2,"min_vram_gb":487.8,"recommended_ram_gb":887.0},"model_id":"thinkingmachines/Inkling","moe":{"active_experts":6,"active_parameters":68824164203,"is_moe":true,"num_experts":256},"parameter_count":"952.4B","parameters_raw":952377623626,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/Inkling-Small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"thinkingmachines/Inkling-Small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"input":0.4,"output":1.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-4.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe_lite","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":2074814,"hf_likes":1800,"matched_hugging_face_id":"zai-org/GLM-4.7-Flash","memory":{"min_ram_gb":17.4,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"zai-org/GLM-4.7-Flash","moe":{"active_experts":4,"active_parameters":3414850312,"is_moe":true,"num_experts":64},"parameter_count":"31.2B","parameters_raw":31221488576,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-01-19","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7-Flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.08},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2025-12","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.205,"input":1.05,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":"2025-04","last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.14,"input":0.75,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Deep Infra","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":null,"catalog_only":true,"config_schema":null,"doc":"https://deepinfra.com/models","env":["DEEPINFRA_API_KEY"],"exclude_models":null,"extra":null,"id":"deepinfra","models":{"ByteDance/Seed-2.0-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"ByteDance/Seed-2.0-code","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 2.0 Code","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"ByteDance/Seed-2.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"ByteDance/Seed-2.0-mini","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 2.0 Mini","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"ByteDance/Seed-2.0-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"ByteDance/Seed-2.0-pro","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 2.0 Pro","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.15,"output":1.15},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"}],"hf_downloads":718615,"hf_likes":1503,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2025-06","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":896905,"hf_likes":1240,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228689764864,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.056,"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","llmfit":{"architecture":"minimax_m3_vl","context_length":1048576,"discovered":false,"gguf_sources":[],"hf_downloads":170183,"hf_likes":1473,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M3","memory":{"min_ram_gb":238.6,"min_vram_gb":218.7,"recommended_ram_gb":397.7},"model_id":"MiniMaxAI/MiniMax-M3","moe":{"active_experts":4,"active_parameters":10000000000,"is_moe":true,"num_experts":128},"parameter_count":"427.0B","parameters_raw":427040140160,"pipeline_tag":"image-text-to-text","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-06-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":524288,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.55},"deprecated":false,"extra":{"attachment":false,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF"}],"hf_downloads":48827,"hf_likes":793,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-21","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":null,"last_updated":"2025-07-21","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B-A22B Instruct 2507","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-30B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-GGUF"}],"hf_downloads":2632870,"hf_likes":922,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B","moe":{"active_experts":8,"active_parameters":3300000000,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":6915474,"hf_likes":732,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.3,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":66536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct Turbo","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"Qwen/Qwen3-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Instruct-GGUF"}],"hf_downloads":258748,"hf_likes":1043,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B Instruct","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"Qwen/Qwen3.5-122B-A10B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2211510,"hf_likes":606,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":2.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2807949,"hf_likes":1028,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-27B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.14,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2397838,"hf_likes":1489,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":"2025-01","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 35B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"input":0.45,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":278133,"hf_likes":1552,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":"2025-01","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 397B A17B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.5-9B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":14256143,"hf_likes":1824,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.32,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6928584,"hf_likes":2266,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.95},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5895532,"hf_likes":2697,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"Qwen/Qwen3.7-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.7-Max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"Qwen/Qwen3.8-2.4T-A95B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","llmfit":{"architecture":"qwen3_5_moe_text","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.8-2.4T-A95B-GGUF"}],"hf_downloads":7932,"hf_likes":1016,"matched_hugging_face_id":"Qwen/Qwen3.8-2.4T-A95B","memory":{"min_ram_gb":1366.9,"min_vram_gb":1253.0,"recommended_ram_gb":2278.2},"model_id":"Qwen/Qwen3.8-2.4T-A95B","moe":{"active_experts":10,"active_parameters":95000000000,"is_moe":true,"num_experts":512},"parameter_count":"2446.2B","parameters_raw":2446182725504,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-08-08","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.8-2.4T-A95B","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.8 2.4T A95B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"Qwen/Qwen3.8-Max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.206,"input":1.65,"output":4.951},"deprecated":false,"extra":{"attachment":true,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.8-Max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":430258,"hf_likes":396,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5","memory":{"min_ram_gb":173.7,"min_vram_gb":159.2,"recommended_ram_gb":289.4},"model_id":"XiaomiMiMo/MiMo-V2.5","moe":{"active_experts":8,"active_parameters":24764886000,"is_moe":true,"num_experts":256},"parameter_count":"310.8B","parameters_raw":310775040000,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/MiMo-V2.5-Pro-GGUF"}],"hf_downloads":54563,"hf_likes":738,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","memory":{"min_ram_gb":571.8,"min_vram_gb":524.1,"recommended_ram_gb":953.0},"model_id":"XiaomiMiMo/MiMo-V2.5-Pro","moe":{"active_experts":8,"active_parameters":71413954340,"is_moe":true,"num_experts":384},"parameter_count":"1023.2B","parameters_raw":1023244718976,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5-Pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.35,"input":0.5,"output":2.15},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":146538,"hf_likes":2458,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1-0528","knowledge":"2024-07","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1-0528","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.32,"output":0.89},"deprecated":false,"extra":{"attachment":false,"description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3-GGUF"}],"hf_downloads":1100153,"hf_likes":4171,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2024-12-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3","knowledge":null,"last_updated":"2024-12-26","lifecycle":null,"limits":{"context":163840,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.24,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":1171226,"hf_likes":3156,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3-0324","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-03-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3-0324","knowledge":null,"last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-03-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":0.25,"output":0.95},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":232218,"hf_likes":826,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-21","lifecycle":null,"limits":{"context":163840,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.1","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":0.26,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1173317,"hf_likes":1467,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":"2024-12","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":163840,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.018,"input":0.09,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2045206,"hf_likes":2109,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.016,"input":0.08,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":1872232,"hf_likes":3464,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1.3,"output":2.6},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1278742,"hf_likes":5452,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1.3,"output":2.6},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":21873,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","memory":{"min_ram_gb":922.3,"min_vram_gb":845.4,"recommended_ram_gb":1537.1},"model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","moe":{"active_experts":6,"active_parameters":107024475595,"is_moe":true,"num_experts":384},"parameter_count":"1650.5B","parameters_raw":1650497936906,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":9990701,"hf_likes":1396,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.38},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/gemma-4-31B-it-GGUF"}],"hf_downloads":9704552,"hf_likes":3575,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":17.5,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"google/gemma-4-31B-it","parameter_count":"31.3B","parameters_raw":31273088876,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-E4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-E4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemma 4 E4B IT","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct-Turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.32},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","knowledge":null,"last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Turbo","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":107564,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.1},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","moe":{"active_experts":1,"active_parameters":43930451431,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401649841664,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B FP8","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/Llama-4-Scout-17B-16E-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF"}],"hf_downloads":430626,"hf_likes":1333,"matched_hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","memory":{"min_ram_gb":60.7,"min_vram_gb":55.6,"recommended_ram_gb":101.2},"model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","moe":{"active_experts":1,"active_parameters":17000000000,"is_moe":true,"num_experts":16},"parameter_count":"108.6B","parameters_raw":108641793536,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","release_date":"2025-04-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true},"family":null,"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":327680,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":808713,"hf_likes":2862,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-01","last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.75,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2024-04","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.136,"input":0.68,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":568317,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.285,"input":2.85,"output":14.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2136775,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","knowledge":null,"last_updated":"2025-07-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 Nemotron Super 49B v1.5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-30B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-30B-A3B","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni 30B A3B Reasoning","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.037,"output":0.17},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.03,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":7966494,"hf_likes":4923,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"stepfun-ai/Step-3.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","llmfit":{"architecture":"step3p7","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Step-3.7-Flash-GGUF"}],"hf_downloads":118145,"hf_likes":0,"matched_hugging_face_id":"stepfun-ai/Step-3.7-Flash","memory":{"min_ram_gb":112.5,"min_vram_gb":103.1,"recommended_ram_gb":187.5},"model_id":"stepfun-ai/Step-3.7-Flash","parameter_count":"201.4B","parameters_raw":201365316160,"pipeline_tag":"image-text-to-text","provider":"stepfun-ai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"stepfun-ai/Step-3.7-Flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"tencent/Hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":12841,"hf_likes":0,"matched_hugging_face_id":"tencent/Hy3","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"tencent/Hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":110771,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling","memory":{"min_ram_gb":532.2,"min_vram_gb":487.8,"recommended_ram_gb":887.0},"model_id":"thinkingmachines/Inkling","moe":{"active_experts":6,"active_parameters":68824164203,"is_moe":true,"num_experts":256},"parameter_count":"952.4B","parameters_raw":952377623626,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/Inkling-Small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":87202,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling-Small","memory":{"min_ram_gb":148.6,"min_vram_gb":136.2,"recommended_ram_gb":247.7},"model_id":"thinkingmachines/Inkling-Small","moe":{"active_experts":6,"active_parameters":19219508292,"is_moe":true,"num_experts":256},"parameter_count":"266.0B","parameters_raw":265956439090,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/Inkling-Small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":27961,"hf_likes":1231,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"input":0.4,"output":1.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":71289,"hf_likes":2054,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-4.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe_lite","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":2021459,"hf_likes":1815,"matched_hugging_face_id":"zai-org/GLM-4.7-Flash","memory":{"min_ram_gb":17.4,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"zai-org/GLM-4.7-Flash","moe":{"active_experts":4,"active_parameters":3414850312,"is_moe":true,"num_experts":64},"parameter_count":"31.2B","parameters_raw":31221488576,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-01-19","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7-Flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.08},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":124645,"hf_likes":2122,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2025-12","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.205,"input":1.05,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":78747,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":"2025-04","last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.14,"input":0.75,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2705686,"hf_likes":4983,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"deepinfra","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Deep Infra","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;