@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/nebius.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.tokenfactory.nebius.com/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.tokenfactory.nebius.com/","env":["NEBIUS_API_KEY"],"exclude_models":null,"extra":null,"id":"nebius","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,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","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":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":196608,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5-fast":{"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,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5-fast","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","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":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"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":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"NousResearch/Hermes-4-405B":{"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,"cache_write":1.25,"input":1,"output":3,"reasoning":3},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-405B","memory":{"min_ram_gb":226.8,"min_vram_gb":207.9,"recommended_ram_gb":378.0},"model_id":"NousResearch/Hermes-4-405B","parameter_count":"405.9B","parameters_raw":405853388800,"pipeline_tag":"text-generation","provider":"NousResearch","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":"NousResearch/Hermes-4-405B","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes-4-405B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-30","retired":false,"tags":null},"NousResearch/Hermes-4-70B":{"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":0.013,"cache_write":0.16,"input":0.13,"output":0.4,"reasoning":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-70B","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"NousResearch/Hermes-4-70B","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"NousResearch","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":"NousResearch/Hermes-4-70B","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes-4-70B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-30","retired":false,"tags":null},"PrimeIntellect/INTELLECT-3":{"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":0.02,"cache_write":0.25,"input":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"PrimeIntellect/INTELLECT-3","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"INTELLECT-3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-25","retired":false,"tags":null},"Qwen/Qwen2.5-VL-72B-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":{"cache_read":0.025,"cache_write":0.31,"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-VL-72B-Instruct-GGUF"}],"hf_downloads":582424,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","memory":{"min_ram_gb":41.0,"min_vram_gb":37.6,"recommended_ram_gb":68.4},"model_id":"Qwen/Qwen2.5-VL-72B-Instruct","parameter_count":"73.4B","parameters_raw":73410777344,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-VL-72B-Instruct","knowledge":"2024-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5-VL-72B-Instruct","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","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":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, 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":59827,"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":false,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":"2025-07","last_updated":"2025-10-04","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507-fast":{"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,"cache_write":0.625,"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B-Thinking-2507-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B-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":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1902844,"hf_likes":822,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"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":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-30B-A3B-Instruct-2507","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","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,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-32B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"Qwen/Qwen3-Embedding-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":3352596,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-8B","memory":{"min_ram_gb":4.2,"min_vram_gb":3.9,"recommended_ram_gb":7.0},"model_id":"Qwen/Qwen3-Embedding-8B","parameter_count":"7.6B","parameters_raw":7567295488,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"open_weights":true,"structured_output":false,"temperature":false},"family":null,"id":"Qwen/Qwen3-Embedding-8B","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding-8B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-10","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"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":0.015,"cache_write":0.18,"input":0.15,"output":1.2,"reasoning":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF"}],"hf_downloads":37095,"hf_likes":492,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","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":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Thinking","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Thinking-fast":{"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":0.015,"cache_write":0.1875,"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Thinking-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Thinking-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","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":0.06,"cache_write":0.75,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","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":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-15","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-fast":{"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,"cache_write":0.75,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-15","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":0.03,"cache_write":0.375,"input":0.3,"output":0.45,"reasoning":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","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":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":163000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-20","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-fast":{"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,"cache_write":0.5,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-fast","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-27","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":0.15,"input":1.75,"output":3.5},"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"]}],"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":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-3-27b-it":{"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":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-27b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-27b-it-GGUF"}],"hf_downloads":847078,"hf_likes":2005,"matched_hugging_face_id":"google/gemma-3-27b-it","memory":{"min_ram_gb":15.3,"min_vram_gb":14.1,"recommended_ram_gb":25.5},"model_id":"google/gemma-3-27b-it","parameter_count":"27.4B","parameters_raw":27432406640,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3-27b-it","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":110000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma-3-27b-it","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-20","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-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":{"cache_read":0.013,"cache_write":0.16,"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":478538,"hf_likes":2936,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2025-08","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-05","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":0.05,"cache_write":0.625,"input":0.5,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","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"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-06","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi-K2.5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"moonshotai/Kimi-K2.5-fast":{"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,"cache_write":0.625,"input":0.5,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5-fast","knowledge":"2025-06","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi-K2.5-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-15","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":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":false,"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":[],"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":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"nebius","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":3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"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":["none","low","medium","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":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1":{"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":0.06,"cache_write":0.75,"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","knowledge":"2024-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.1-Nemotron-Ultra-253B-v1","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B":{"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":0.006,"cache_write":0.075,"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","knowledge":"2025-05","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Nano-30B-A3B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-08-10","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-Omni":{"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":0.006,"cache_write":0.075,"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-Omni","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":65536,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Nano-Omni","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"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":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":"2026-02","last_updated":"2026-03-12","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Super-120B-A12B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-03-11","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":{"cache_read":0.015,"cache_write":0.18,"input":0.15,"output":0.6,"reasoning":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","interleaved":{"field":"reasoning_content"},"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":"2025-09","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-10","retired":false,"tags":null},"openai/gpt-oss-120b-fast":{"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,"cache_write":0.125,"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b-fast","knowledge":"2025-06","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-06-10","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":0.1,"cache_write":1,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","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":false,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2026-01","last_updated":"2026-03-10","lifecycle":null,"limits":{"context":200000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-03-01","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":{"input":1.4,"output":4.4},"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":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":432000,"output":432000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Nebius Token Factory","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.tokenfactory.nebius.com/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.tokenfactory.nebius.com/","env":["NEBIUS_API_KEY"],"exclude_models":null,"extra":null,"id":"nebius","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,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","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":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":196608,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5-fast":{"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,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5-fast","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","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":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"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":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"NousResearch/Hermes-4-405B":{"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,"cache_write":1.25,"input":1,"output":3,"reasoning":3},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-405B","memory":{"min_ram_gb":226.8,"min_vram_gb":207.9,"recommended_ram_gb":378.0},"model_id":"NousResearch/Hermes-4-405B","parameter_count":"405.9B","parameters_raw":405853388800,"pipeline_tag":"text-generation","provider":"NousResearch","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":"NousResearch/Hermes-4-405B","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes-4-405B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-30","retired":false,"tags":null},"NousResearch/Hermes-4-70B":{"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":0.013,"cache_write":0.16,"input":0.13,"output":0.4,"reasoning":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-70B","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"NousResearch/Hermes-4-70B","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"NousResearch","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":"NousResearch/Hermes-4-70B","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes-4-70B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-30","retired":false,"tags":null},"PrimeIntellect/INTELLECT-3":{"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":0.02,"cache_write":0.25,"input":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"PrimeIntellect/INTELLECT-3","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"INTELLECT-3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-25","retired":false,"tags":null},"Qwen/Qwen2.5-VL-72B-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":{"cache_read":0.025,"cache_write":0.31,"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-VL-72B-Instruct-GGUF"}],"hf_downloads":483150,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","memory":{"min_ram_gb":41.0,"min_vram_gb":37.6,"recommended_ram_gb":68.4},"model_id":"Qwen/Qwen2.5-VL-72B-Instruct","parameter_count":"73.4B","parameters_raw":73410777344,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-VL-72B-Instruct","knowledge":"2024-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5-VL-72B-Instruct","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","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":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, 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":false,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":"2025-07","last_updated":"2025-10-04","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507-fast":{"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,"cache_write":0.625,"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B-Thinking-2507-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B-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":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1903290,"hf_likes":827,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"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":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-30B-A3B-Instruct-2507","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","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,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-32B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"Qwen/Qwen3-Embedding-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":2869862,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-8B","memory":{"min_ram_gb":4.2,"min_vram_gb":3.9,"recommended_ram_gb":7.0},"model_id":"Qwen/Qwen3-Embedding-8B","parameter_count":"7.6B","parameters_raw":7567295488,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"open_weights":true,"structured_output":false,"temperature":false},"family":null,"id":"Qwen/Qwen3-Embedding-8B","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding-8B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-10","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"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":0.015,"cache_write":0.18,"input":0.15,"output":1.2,"reasoning":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF"}],"hf_downloads":34032,"hf_likes":494,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","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":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","knowledge":"2025-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Thinking","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Thinking-fast":{"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":0.015,"cache_write":0.1875,"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Thinking-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Thinking-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-25","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":0.06,"cache_write":0.75,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","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":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-15","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-fast":{"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,"cache_write":0.75,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-fast","knowledge":"2025-07","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-07-15","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":0.03,"cache_write":0.375,"input":0.3,"output":0.45,"reasoning":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","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":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":"2025-11","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":163000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-20","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-fast":{"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,"cache_write":0.5,"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-fast","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-27","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":0.14,"input":0.14,"output":0.28},"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":"effort","values":["none","low","high","max"]}],"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":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-04-24","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":0.15,"input":1.75,"output":3.5},"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"]}],"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":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-3-27b-it":{"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":0.01,"cache_write":0.125,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-27b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-27b-it-GGUF"}],"hf_downloads":769964,"hf_likes":2007,"matched_hugging_face_id":"google/gemma-3-27b-it","memory":{"min_ram_gb":15.3,"min_vram_gb":14.1,"recommended_ram_gb":25.5},"model_id":"google/gemma-3-27b-it","parameter_count":"27.4B","parameters_raw":27432406640,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-3-27b-it","knowledge":"2025-10","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":110000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma-3-27b-it","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-20","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-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":{"cache_read":0.013,"cache_write":0.16,"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":312172,"hf_likes":2952,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2025-08","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-05","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":0.05,"cache_write":0.625,"input":0.5,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","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"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-06","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi-K2.5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"moonshotai/Kimi-K2.5-fast":{"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,"cache_write":0.625,"input":0.5,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5-fast","knowledge":"2025-06","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi-K2.5-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-12-15","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":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":false,"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":[],"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":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"nebius","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":3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"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":["none","low","medium","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":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1":{"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":0.06,"cache_write":0.75,"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","llmfit":{"architecture":"nemotron-nas","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","memory":{"min_ram_gb":141.6,"min_vram_gb":129.8,"recommended_ram_gb":236.0},"model_id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","parameter_count":"253.4B","parameters_raw":253401268224,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","knowledge":"2024-12","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.1-Nemotron-Ultra-253B-v1","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B":{"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":0.006,"cache_write":0.075,"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","knowledge":"2025-05","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Nano-30B-A3B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-08-10","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-Omni":{"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":0.006,"cache_write":0.075,"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-Omni","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":65536,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Nano-Omni","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"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":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":"2026-02","last_updated":"2026-03-12","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron-3-Super-120B-A12B","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-03-11","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":{"cache_read":0.015,"cache_write":0.18,"input":0.15,"output":0.6,"reasoning":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","interleaved":{"field":"reasoning_content"},"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":"2025-09","last_updated":"2026-02-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-01-10","retired":false,"tags":null},"openai/gpt-oss-120b-fast":{"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,"cache_write":0.125,"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b-fast","knowledge":"2025-06","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":8000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b-fast","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2025-06-10","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":0.1,"cache_write":1,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","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":false,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2026-01","last_updated":"2026-03-10","lifecycle":null,"limits":{"context":200000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-03-01","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":{"input":1.4,"output":4.4},"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":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":432000,"output":432000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"nebius","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Nebius Token Factory","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/neon.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "neon",
-  "claude-haiku-4-5" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-6" | "claude-opus-4-7" | "claude-opus-4-8" | "claude-sonnet-4" | "claude-sonnet-4-5" | "claude-sonnet-4-6" | "gemini-2-5-flash" | "gemini-2-5-pro" | "gemini-3-1-flash-lite" | "gemini-3-1-pro" | "gemini-3-5-flash" | "gemini-3-flash" | "gemini-3-pro" | "gemma-3-12b" | "gpt-5" | "gpt-5-1" | "gpt-5-1-codex-max" | "gpt-5-1-codex-mini" | "gpt-5-2" | "gpt-5-2-codex" | "gpt-5-3-codex" | "gpt-5-4" | "gpt-5-4-mini" | "gpt-5-4-nano" | "gpt-5-mini" | "gpt-5-nano" | "gpt-oss-120b" | "gpt-oss-20b" | "llama-4-maverick" | "meta-llama-3-1-8b-instruct" | "meta-llama-3-3-70b-instruct" | "qwen3-next-80b-a3b-instruct" | "qwen35-122b-a10b"
+  "claude-fable-5" | "claude-haiku-4-5" | "claude-opus-4-1" | "claude-opus-4-5" | "claude-opus-4-6" | "claude-opus-4-7" | "claude-opus-4-8" | "claude-opus-5" | "claude-sonnet-4-5" | "claude-sonnet-4-6" | "claude-sonnet-5" | "gemini-3-1-flash-lite" | "gemini-3-1-pro" | "gemini-3-5-flash" | "gemini-3-5-flash-lite" | "gemini-3-6-flash" | "gemini-3-flash" | "gemma-3-12b" | "glm-5-2" | "gpt-5" | "gpt-5-1" | "gpt-5-2" | "gpt-5-3-codex" | "gpt-5-4" | "gpt-5-4-mini" | "gpt-5-4-nano" | "gpt-5-5" | "gpt-5-5-pro" | "gpt-5-6-luna" | "gpt-5-6-sol" | "gpt-5-6-terra" | "gpt-5-mini" | "gpt-5-nano" | "gpt-oss-120b" | "gpt-oss-20b" | "inkling" | "kimi-k3" | "llama-4-maverick" | "meta-llama-3-1-8b-instruct" | "meta-llama-3-3-70b-instruct" | "qwen3-next-80b-a3b-instruct" | "qwen35-122b-a10b"
 >;
 export default provider;