@agentjido/llmdb 2026.8.2

package/dist/providers/pioneer.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.pioneer.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://agent.pioneer.ai/llms.txt","env":["PIONEER_API_KEY"],"exclude_models":null,"extra":null,"id":"pioneer","models":{"HuggingFaceTB/SmolLM3-3B-Base":{"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,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"smollm3","context_length":65536,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/SmolLM3-3B-Base-GGUF"}],"hf_downloads":159328,"hf_likes":167,"matched_hugging_face_id":"HuggingFaceTB/SmolLM3-3B-Base","memory":{"min_ram_gb":1.7,"min_vram_gb":1.6,"recommended_ram_gb":2.9},"model_id":"HuggingFaceTB/SmolLM3-3B-Base","parameter_count":"3.1B","parameters_raw":3075098624,"pipeline_tag":"text-generation","provider":"huggingfacetb","quantization":"Q4_K_M","release_date":"2025-06-19","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"HuggingFaceTB/SmolLM3-3B-Base","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"SmolLM3 3B Base","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"LiquidAI/LFM2-24B-A2B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.03,"input":0.03,"output":0.12},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"lfm2_moe","context_length":128000,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/LFM2-24B-A2B-GGUF"}],"hf_downloads":3687,"hf_likes":340,"matched_hugging_face_id":"LiquidAI/LFM2-24B-A2B","memory":{"min_ram_gb":13.3,"min_vram_gb":12.2,"recommended_ram_gb":22.2},"model_id":"LiquidAI/LFM2-24B-A2B","moe":{"active_experts":4,"active_parameters":2300000000,"is_moe":true,"num_experts":64},"parameter_count":"23.8B","parameters_raw":23843661440,"pipeline_tag":"text-generation","provider":"Liquid AI","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"LiquidAI/LFM2-24B-A2B","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"LFM2 24B A2B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-01-31","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.279,"cache_write":0.279,"input":0.279,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":917214,"hf_likes":1236,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.3,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","interleaved":{"field":"reasoning_content"},"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":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/Qwen3-1.7B-Base":{"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":0.1,"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3","context_length":32768,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3-1.7B-Base-GGUF"}],"hf_downloads":866993,"hf_likes":75,"matched_hugging_face_id":"Qwen/Qwen3-1.7B-Base","memory":{"min_ram_gb":1.0,"min_vram_gb":0.9,"recommended_ram_gb":2.0},"model_id":"Qwen/Qwen3-1.7B-Base","parameter_count":"1.7B","parameters_raw":1720574976,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-28","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3-1.7B-Base","knowledge":null,"last_updated":"2025-03-31","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 1.7B Base","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-03-31","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.9,"cache_write":0.9,"input":0.9,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-4B-Base":{"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,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3","context_length":32768,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3-4B-Base-GGUF"}],"hf_downloads":713430,"hf_likes":96,"matched_hugging_face_id":"Qwen/Qwen3-4B-Base","memory":{"min_ram_gb":2.2,"min_vram_gb":2.1,"recommended_ram_gb":3.7},"model_id":"Qwen/Qwen3-4B-Base","parameter_count":"4.0B","parameters_raw":4022468096,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-28","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3-4B-Base","knowledge":null,"last_updated":"2025-03-31","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 4B Base","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-03-31","retired":false,"tags":null},"Qwen/Qwen3-4B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.2,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-4B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-4B-Instruct-2507-GGUF"}],"hf_downloads":3213183,"hf_likes":909,"matched_hugging_face_id":"Qwen/Qwen3-4B-Instruct-2507","memory":{"min_ram_gb":2.2,"min_vram_gb":2.1,"recommended_ram_gb":3.7},"model_id":"Qwen/Qwen3-4B-Instruct-2507","parameter_count":"4.0B","parameters_raw":4022468096,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-08-05","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3-4B-Instruct-2507","knowledge":null,"last_updated":"2025-07-31","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 4B Instruct","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"Qwen/Qwen3-8B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.2,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-8B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-8B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-8B-GGUF"}],"hf_downloads":15911466,"hf_likes":1273,"matched_hugging_face_id":"Qwen/Qwen3-8B","memory":{"min_ram_gb":4.6,"min_vram_gb":4.2,"recommended_ram_gb":7.6},"model_id":"Qwen/Qwen3-8B","parameter_count":"8.2B","parameters_raw":8190735360,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3-8B","knowledge":"2025-03-31","last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 8B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-03-31","retired":false,"tags":null},"Qwen/Qwen3.5-9B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":0.3,"input":0.3,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":12236962,"hf_likes":1781,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.6,"cache_write":0.6,"input":0.6,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"cache_write":0.175,"input":0.14,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"cache_write":0.14,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":359231,"hf_likes":383,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5","memory":{"min_ram_gb":173.7,"min_vram_gb":159.2,"recommended_ram_gb":289.4},"model_id":"XiaomiMiMo/MiMo-V2.5","moe":{"active_experts":8,"active_parameters":24764886000,"is_moe":true,"num_experts":256},"parameter_count":"310.8B","parameters_raw":310775040000,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0036,"cache_write":0.435,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/MiMo-V2.5-Pro-GGUF"}],"hf_downloads":53020,"hf_likes":727,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","memory":{"min_ram_gb":571.8,"min_vram_gb":524.1,"recommended_ram_gb":953.0},"model_id":"XiaomiMiMo/MiMo-V2.5-Pro","moe":{"active_experts":8,"active_parameters":71413954340,"is_moe":true,"num_experts":384},"parameter_count":"1023.2B","parameters_raw":1023244718976,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5-Pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"claude-haiku-4-5":{"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":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-haiku-4-5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5 (latest)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-opus-4-1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1 (latest)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5":{"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":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-opus-4-5","knowledge":"2025-05","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5 (latest)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"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":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-sonnet-4-5":{"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":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-02-17","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":0.0197,"cache_write":0.1,"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"pioneer","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":0.003625,"cache_write":0.435,"input":0.435,"output":0.87},"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":"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":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"fastino/gliguard-LLMGuardrails-300M":{"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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliguard-LLMGuardrails-300M","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiGuard LLM Guardrails 300M","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"fastino/gliner2-base-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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliner2-base-v1","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiNER2 Base","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"fastino/gliner2-large-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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliner2-large-v1","knowledge":null,"last_updated":"2025-06-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiNER2 Large","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"fastino/gliner2-multi-large-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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliner2-multi-large-v1","knowledge":null,"last_updated":"2025-11-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiNER2 Multi Large","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-11-30","retired":false,"tags":null},"fastino/gliner2-multi-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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliner2-multi-v1","knowledge":null,"last_updated":"2025-11-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiNER2 Multi","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-11-30","retired":false,"tags":null},"fastino/gliner2-privacy-filter-PII-multi":{"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":0.15,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","open_weights":false,"temperature":true},"family":null,"id":"fastino/gliner2-privacy-filter-PII-multi","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLiNER2 Privacy Filter PII (Multi)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"gemini-3-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":0.05,"cache_write":0.083333,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-3.1-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.5-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":0.15,"cache_write":0.083333,"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/diffusiongemma-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":0.5,"input":0.5,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Gemini model for general assistance, reasoning, and multimodal workflows","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"diffusion_gemma","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/diffusiongemma-26B-A4B-it-GGUF"}],"hf_downloads":2028422,"hf_likes":0,"matched_hugging_face_id":"google/diffusiongemma-26B-A4B-it","memory":{"min_ram_gb":14.4,"min_vram_gb":13.2,"recommended_ram_gb":24.1},"model_id":"google/diffusiongemma-26B-A4B-it","moe":{"active_experts":8,"active_parameters":2824475807,"is_moe":true,"num_experts":128},"parameter_count":"25.8B","parameters_raw":25823778864,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"google/diffusiongemma-26B-A4B-it","knowledge":null,"last_updated":"2026-05-31","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DiffusionGemma 26B-A4B IT","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-05-31","retired":false,"tags":null},"google/gemma-3-4b-pt":{"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,"cache_write":0.15,"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"gemma3","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":73031,"hf_likes":0,"matched_hugging_face_id":"google/gemma-3-4b-pt","memory":{"min_ram_gb":2.4,"min_vram_gb":2.2,"recommended_ram_gb":4.0},"model_id":"google/gemma-3-4b-pt","parameter_count":"4.3B","parameters_raw":4300079472,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"google/gemma-3-4b-pt","knowledge":null,"last_updated":"2025-02-28","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 3 4B (Pretrained)","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-02-28","retired":false,"tags":null},"google/gemma-4-12B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":0.25,"input":0.25,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"google/gemma-4-12B-it","knowledge":null,"last_updated":"2026-05-31","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 12B IT","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-05-31","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":0.5,"input":0.5,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-E2B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":0.1,"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-E2B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemma 4 E2B IT","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-E4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.2,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-E4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Gemma 4 E4B IT","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":2,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.4,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano":{"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":0.1,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o":{"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":1.25,"cache_write":2.5,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.15,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.25,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-nano":{"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":0.005,"cache_write":0.05,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"cache_write":1.25,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.3-codex":{"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":0.175,"cache_write":1.75,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"gpt-5.4":{"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":0.25,"cache_write":2.5,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.75,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.2,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":1047576,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.5":{"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":0.5,"cache_write":5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"meta-llama/Llama-3.1-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.2,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.1-8B-Instruct-GGUF"}],"hf_downloads":7886695,"hf_likes":6455,"matched_hugging_face_id":"meta-llama/Llama-3.1-8B-Instruct","memory":{"min_ram_gb":4.5,"min_vram_gb":4.1,"recommended_ram_gb":7.5},"model_id":"meta-llama/Llama-3.1-8B-Instruct","parameter_count":"8.0B","parameters_raw":8030261248,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-07-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"meta-llama/Llama-3.1-8B-Instruct","knowledge":"2023-12-31","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-06-30","retired":false,"tags":null},"meta-llama/Llama-3.2-1B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":0.1,"input":0.1,"output":0.201},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.2-1B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.2-1B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.2-1B-Instruct-GGUF"}],"hf_downloads":10100649,"hf_likes":1550,"matched_hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","memory":{"min_ram_gb":1.0,"min_vram_gb":0.6,"recommended_ram_gb":2.0},"model_id":"meta-llama/Llama-3.2-1B-Instruct","parameter_count":"1.2B","parameters_raw":1235814400,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-09-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"meta-llama/Llama-3.2-1B-Instruct","knowledge":"2023-12-31","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":131072,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 1B Instruct","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-08-31","retired":false,"tags":null},"meta-llama/Llama-3.2-3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":0.1,"input":0.1,"output":0.335},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.2-3B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.2-3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.2-3B-Instruct-GGUF"}],"hf_downloads":1461226,"hf_likes":2387,"matched_hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","memory":{"min_ram_gb":1.8,"min_vram_gb":1.6,"recommended_ram_gb":3.0},"model_id":"meta-llama/Llama-3.2-3B-Instruct","parameter_count":"3.2B","parameters_raw":3212749824,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-09-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"meta-llama/Llama-3.2-3B-Instruct","knowledge":"2023-12-31","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":131072,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-08-31","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":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.9,"cache_write":0.9,"input":0.9,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","interleaved":{"field":"reasoning_content"},"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,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"mistral-medium-3.5":{"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":1.5,"cache_write":1.5,"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistral-medium-3.5","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistralai/Mistral-7B-Instruct-v0.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.2,"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"mistralai/Mistral-7B-Instruct-v0.3","knowledge":null,"last_updated":"2023-04-30","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral 7B Instruct v0.3","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2023-04-30","retired":false,"tags":null},"mistralai/Mistral-Nemo-Instruct-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.02,"input":0.02,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"mistralai/Mistral-Nemo-Instruct-2407","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"mistralai/Mistral-Small-4-119B-2603":{"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":0.15,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"mistralai/Mistral-Small-4-119B-2603","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.34,"cache_write":0.95,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"cache_write":0.95,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"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":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16":{"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":0.05,"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-GGUF"}],"hf_downloads":920209,"hf_likes":805,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","moe":{"active_experts":6,"active_parameters":3000000000,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577937344,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8":{"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":0.09,"cache_write":0.09,"input":0.09,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":210668,"hf_likes":271,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","memory":{"min_ram_gb":69.1,"min_vram_gb":63.3,"recommended_ram_gb":115.1},"model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","moe":{"active_experts":22,"active_parameters":11226390744,"is_moe":true,"num_experts":512},"parameter_count":"123.6B","parameters_raw":123611012096,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-03-10","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16":{"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,"cache_write":0.5,"input":0.5,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":451729,"hf_likes":302,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","memory":{"min_ram_gb":313.2,"min_vram_gb":287.1,"recommended_ram_gb":522.0},"model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","moe":{"active_experts":22,"active_parameters":50907017398,"is_moe":true,"num_experts":512},"parameter_count":"560.5B","parameters_raw":560524578816,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-06-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1000000,"output":65000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-04","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":0.15,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","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","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"cache_write":0.07,"input":0.07,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"pioneer/auto":{"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":null,"deprecated":false,"extra":{"attachment":true,"description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"pioneer/auto","knowledge":null,"last_updated":"2025-06-29","lifecycle":null,"limits":{"context":1048576,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Pioneer Auto","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"qwen3.6-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":0.0375,"cache_write":0.234375,"input":0.1875,"output":1.125},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-flash","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Flash","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen3.6-max-preview":{"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":0.208,"cache_write":1.3,"input":1.04,"output":6.24},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"qwen3.6-max-preview","knowledge":"2025-04","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 Max Preview","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"qwen3.6-plus":{"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":0.065,"cache_write":0.40625,"input":0.325,"output":1.95},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"qwen3.7-max":{"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":0.25,"cache_write":1.5625,"input":1.25,"output":3.75},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"qwen3.7-plus":{"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":0.064,"cache_write":0.4,"input":0.32,"output":1.28},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"sakana/fugu-ultra":{"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":0.5,"cache_write":5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"sakana/fugu-ultra","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-15","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.182,"cache_write":0.98,"input":0.98,"output":3.08},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":1.4,"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","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"pioneer","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Pioneer","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/poe.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "poe",
+  "anthropic/claude-haiku-3" | "anthropic/claude-haiku-3.5" | "anthropic/claude-haiku-4.5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4.1" | "anthropic/claude-opus-4.5" | "anthropic/claude-opus-4.6" | "anthropic/claude-opus-4.7" | "anthropic/claude-opus-4.8" | "anthropic/claude-sonnet-3.5" | "anthropic/claude-sonnet-3.5-june" | "anthropic/claude-sonnet-3.7" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4.5" | "anthropic/claude-sonnet-4.6" | "cerebras/gpt-oss-120b-cs" | "cerebras/llama-3.1-8b-cs" | "cerebras/llama-3.3-70b-cs" | "cerebras/qwen3-235b-2507-cs" | "cerebras/qwen3-32b-cs" | "elevenlabs/elevenlabs-music" | "elevenlabs/elevenlabs-v2.5-turbo" | "elevenlabs/elevenlabs-v3" | "empiriolabs/deepseek-v4-flash-el" | "empiriolabs/deepseek-v4-pro-el" | "fireworks-ai/kimi-k2.5-fw" | "google/gemini-2.0-flash" | "google/gemini-2.0-flash-lite" | "google/gemini-2.5-flash" | "google/gemini-2.5-flash-lite" | "google/gemini-2.5-pro" | "google/gemini-3-flash" | "google/gemini-3-pro" | "google/gemini-3.1-flash-lite" | "google/gemini-3.1-pro" | "google/gemini-3.5-flash" | "google/gemini-deep-research" | "google/gemma-4-31b" | "google/imagen-3" | "google/imagen-3-fast" | "google/imagen-4" | "google/imagen-4-fast" | "google/imagen-4-ultra" | "google/lyria" | "google/nano-banana" | "google/nano-banana-pro" | "google/veo-2" | "google/veo-3" | "google/veo-3-fast" | "google/veo-3.1" | "google/veo-3.1-fast" | "ideogramai/ideogram" | "ideogramai/ideogram-v2" | "ideogramai/ideogram-v2a" | "ideogramai/ideogram-v2a-turbo" | "lumalabs/ray2" | "novita/deepseek-v3.2" | "novita/glm-4.6" | "novita/glm-4.6v" | "novita/glm-4.7" | "novita/glm-4.7-flash" | "novita/glm-4.7-n" | "novita/glm-5" | "novita/kimi-k2-thinking" | "novita/kimi-k2.5" | "novita/kimi-k2.6" | "novita/minimax-m2.1" | "openai/chatgpt-4o-latest" | "openai/dall-e-3" | "openai/gpt-3.5-turbo" | "openai/gpt-3.5-turbo-instruct" | "openai/gpt-3.5-turbo-raw" | "openai/gpt-4-classic" | "openai/gpt-4-classic-0314" | "openai/gpt-4-turbo" | "openai/gpt-4.1" | "openai/gpt-4.1-mini" | "openai/gpt-4.1-nano" | "openai/gpt-4o" | "openai/gpt-4o-aug" | "openai/gpt-4o-mini" | "openai/gpt-4o-mini-search" | "openai/gpt-4o-search" | "openai/gpt-5" | "openai/gpt-5-chat" | "openai/gpt-5-codex" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5-pro" | "openai/gpt-5.1" | "openai/gpt-5.1-codex" | "openai/gpt-5.1-codex-max" | "openai/gpt-5.1-codex-mini" | "openai/gpt-5.1-instant" | "openai/gpt-5.2" | "openai/gpt-5.2-codex" | "openai/gpt-5.2-instant" | "openai/gpt-5.2-pro" | "openai/gpt-5.3-codex" | "openai/gpt-5.3-codex-spark" | "openai/gpt-5.3-instant" | "openai/gpt-5.4" | "openai/gpt-5.4-mini" | "openai/gpt-5.4-nano" | "openai/gpt-5.4-pro" | "openai/gpt-5.5" | "openai/gpt-5.5-pro" | "openai/gpt-image-1" | "openai/gpt-image-1-mini" | "openai/gpt-image-1.5" | "openai/gpt-image-2" | "openai/o1" | "openai/o1-pro" | "openai/o3" | "openai/o3-deep-research" | "openai/o3-mini" | "openai/o3-mini-high" | "openai/o3-pro" | "openai/o4-mini" | "openai/o4-mini-deep-research" | "openai/sora-2" | "openai/sora-2-pro" | "poetools/claude-code" | "runwayml/runway" | "runwayml/runway-gen-4-turbo" | "stabilityai/stablediffusionxl" | "topazlabs-co/topazlabs" | "trytako/tako" | "xai/grok-3" | "xai/grok-3-mini" | "xai/grok-4" | "xai/grok-4-fast-non-reasoning" | "xai/grok-4-fast-reasoning" | "xai/grok-4.1-fast-non-reasoning" | "xai/grok-4.1-fast-reasoning" | "xai/grok-4.20-multi-agent" | "xai/grok-code-fast-1"
+>;
+export default provider;