@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/siliconflow.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.siliconflow.com/v1","catalog_only":true,"config_schema":null,"doc":"https://cloud.siliconflow.com/models","env":["SILICONFLOW_API_KEY"],"exclude_models":null,"extra":null,"id":"siliconflow","models":{"ByteDance-Seed/Seed-OSS-36B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.21,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","llmfit":{"architecture":"seed_oss","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Seed-OSS-36B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Seed-OSS-36B-Instruct-GGUF"}],"hf_downloads":41234,"hf_likes":505,"matched_hugging_face_id":"ByteDance-Seed/Seed-OSS-36B-Instruct","memory":{"min_ram_gb":20.2,"min_vram_gb":18.5,"recommended_ram_gb":33.7},"model_id":"ByteDance-Seed/Seed-OSS-36B-Instruct","parameter_count":"36.2B","parameters_raw":36151104512,"pipeline_tag":"text-generation","provider":"bytedance-seed","quantization":"Q4_K_M","release_date":"2025-08-20","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ByteDance-Seed/Seed-OSS-36B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":197000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMaxAI/MiniMax-M2.5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen2.5-72B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.59},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-72B-Instruct-GGUF"}],"hf_downloads":445760,"hf_likes":968,"matched_hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","memory":{"min_ram_gb":40.6,"min_vram_gb":37.2,"recommended_ram_gb":67.7},"model_id":"Qwen/Qwen2.5-72B-Instruct","parameter_count":"72.7B","parameters_raw":72706203648,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-72B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":33000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen2.5-72B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"Qwen/Qwen2.5-7B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-7B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-7B-Instruct-GGUF"}],"hf_downloads":12160501,"hf_likes":1456,"matched_hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","memory":{"min_ram_gb":4.3,"min_vram_gb":3.9,"recommended_ram_gb":7.1},"model_id":"Qwen/Qwen2.5-7B-Instruct","parameter_count":"7.6B","parameters_raw":7615616512,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-7B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":33000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen2.5-7B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"Qwen/Qwen3-14B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-14B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-14B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-14B-GGUF"}],"hf_downloads":2837654,"hf_likes":436,"matched_hugging_face_id":"Qwen/Qwen3-14B","memory":{"min_ram_gb":8.3,"min_vram_gb":7.6,"recommended_ram_gb":13.8},"model_id":"Qwen/Qwen3-14B","parameter_count":"14.8B","parameters_raw":14768307200,"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":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-14B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-14B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-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":{"input":0.13,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF"}],"hf_downloads":29970,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-235B-A22B-Thinking-2507","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1902844,"hf_likes":822,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-30B-A3B-Instruct-2507","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-32B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","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":{"input":0.06,"output":0.06},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","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":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-8B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-8B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Coder-30B-A3B-Instruct-GGUF"}],"hf_downloads":1462772,"hf_likes":1187,"matched_hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-31","source":"llmfit","use_case":"Code generation and completion"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-01","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91304,"hf_likes":1357,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Instruct-GGUF"}],"hf_downloads":1789796,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-235B-A22B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-04","retired":false,"tags":null},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Thinking-GGUF"}],"hf_downloads":11877,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-235B-A22B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-04","retired":false,"tags":null},"Qwen/Qwen3-VL-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":815503,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-30B-A3B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-05","retired":false,"tags":null},"Qwen/Qwen3-VL-30B-A3B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":39960,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-30B-A3B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-11","retired":false,"tags":null},"Qwen/Qwen3-VL-32B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-32B-Instruct-GGUF"}],"hf_downloads":2809038,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","memory":{"min_ram_gb":18.6,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"Qwen/Qwen3-VL-32B-Instruct","parameter_count":"33.4B","parameters_raw":33357390064,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-32B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-32B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-21","retired":false,"tags":null},"Qwen/Qwen3-VL-32B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-32B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-32B-Thinking-GGUF"}],"hf_downloads":19714,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-32B-Thinking","memory":{"min_ram_gb":18.6,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"Qwen/Qwen3-VL-32B-Thinking","parameter_count":"33.4B","parameters_raw":33357390064,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-32B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-32B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-21","retired":false,"tags":null},"Qwen/Qwen3-VL-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.68},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":4896095,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"Qwen/Qwen3-VL-8B-Instruct","parameter_count":"8.8B","parameters_raw":8767123696,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-8B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-8B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"Qwen/Qwen3.5-122B-A10B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":2.08},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2114418,"hf_likes":603,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2666483,"hf_likes":1023,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-27B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.24,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2582188,"hf_likes":1480,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.39,"output":2.34},"deprecated":false,"extra":{"attachment":false,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":416324,"hf_likes":1546,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-15","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":12236962,"hf_likes":1781,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3.5-9B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-03-03","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"siliconflow","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.6},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"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":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"baidu/ERNIE-4.5-300B-A47B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ernie","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"baidu/ERNIE-4.5-300B-A47B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"baidu/ERNIE-4.5-300B-A47B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-02","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":2.18},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":9604023,"hf_likes":13537,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-R1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3-GGUF"}],"hf_downloads":1177282,"hf_likes":4110,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2024-12-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":273040,"hf_likes":825,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1-Terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":16978,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1-Terminus","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.1-Terminus","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1238427,"hf_likes":1462,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":null,"last_updated":"2025-12-03","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.2","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-Exp":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.41},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":252109,"hf_likes":993,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2-Exp","moe":{"active_experts":8,"active_parameters":54617567164,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-Exp","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.2-Exp","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-10","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":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":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":[{"max":32768,"min":128,"type":"budget_tokens"}],"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":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"siliconflow","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":0.145,"input":1.74,"output":3.48},"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":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"inclusionAI/Ling-flash-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","llmfit":{"architecture":"bailing_moe","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"inclusionAI/Ling-flash-2.0","memory":{"min_ram_gb":57.5,"min_vram_gb":52.7,"recommended_ram_gb":95.8},"model_id":"inclusionAI/Ling-flash-2.0","parameter_count":"102.9B","parameters_raw":102889705216,"pipeline_tag":"text-generation","provider":"inclusionai","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"inclusionAI/Ling-flash-2.0","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI/Ling-flash-2.0","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-18","retired":false,"tags":null},"moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"moonshotai/Kimi-K2.5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.77,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","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":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"moonshotai/Kimi-K2.6","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"openai/gpt-oss-120b","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-13","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.04,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"openai/gpt-oss-20b","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"stepfun-ai/Step-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":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","llmfit":{"architecture":"step3p5","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/Step-3.5-Flash-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Step-3.5-Flash-GGUF"}],"hf_downloads":94390,"hf_likes":829,"matched_hugging_face_id":"stepfun-ai/Step-3.5-Flash","memory":{"min_ram_gb":111.4,"min_vram_gb":102.1,"recommended_ram_gb":185.7},"model_id":"stepfun-ai/Step-3.5-Flash","parameter_count":"199.4B","parameters_raw":199384301376,"pipeline_tag":"text-generation","provider":"stepfun-ai","quantization":"Q4_K_M","release_date":"2026-02-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"stepfun-ai/Step-3.5-Flash","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"stepfun-ai/Step-3.5-Flash","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"tencent/Hunyuan-A13B-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":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","llmfit":{"architecture":"hunyuan_v1_moe","context_length":32768,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Hunyuan-A13B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Hunyuan-A13B-Instruct-GGUF"}],"hf_downloads":50454,"hf_likes":796,"matched_hugging_face_id":"tencent/Hunyuan-A13B-Instruct","memory":{"min_ram_gb":44.9,"min_vram_gb":41.2,"recommended_ram_gb":74.9},"model_id":"tencent/Hunyuan-A13B-Instruct","parameter_count":"80.4B","parameters_raw":80393183232,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2025-06-25","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"tencent/Hunyuan-A13B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"tencent/Hunyuan-A13B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"tencent/Hy3-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":0.029,"input":0.066,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":64911,"hf_likes":300,"matched_hugging_face_id":"tencent/Hy3-preview","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3-preview","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2026-04-13","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"tencent/Hy3-preview","knowledge":null,"last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3 preview","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"zai-org/GLM-4.5-Air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.86},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-Air-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5-Air-GGUF"}],"hf_downloads":441341,"hf_likes":625,"matched_hugging_face_id":"zai-org/GLM-4.5-Air","memory":{"min_ram_gb":61.7,"min_vram_gb":56.6,"recommended_ram_gb":102.9},"model_id":"zai-org/GLM-4.5-Air","moe":{"active_experts":8,"active_parameters":12082527713,"is_moe":true,"num_experts":128},"parameter_count":"110.5B","parameters_raw":110468824832,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.5-Air","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-4.5-Air","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.95,"output":2.55},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":205000,"output":205000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":0,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-08","lifecycle":null,"limits":{"context":205000,"output":205000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-5.1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-08","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":0,"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":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1049000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai-org/GLM-5V-Turbo":{"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":0.24,"cache_write":0,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"zai-org/GLM-5V-Turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"zai-org/GLM-5V-Turbo","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null}},"name":"SiliconFlow","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.siliconflow.com/v1","catalog_only":true,"config_schema":null,"doc":"https://cloud.siliconflow.com/models","env":["SILICONFLOW_API_KEY"],"exclude_models":null,"extra":null,"id":"siliconflow","models":{"ByteDance-Seed/Seed-OSS-36B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.21,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","llmfit":{"architecture":"seed_oss","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Seed-OSS-36B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Seed-OSS-36B-Instruct-GGUF"}],"hf_downloads":41443,"hf_likes":505,"matched_hugging_face_id":"ByteDance-Seed/Seed-OSS-36B-Instruct","memory":{"min_ram_gb":20.2,"min_vram_gb":18.5,"recommended_ram_gb":33.7},"model_id":"ByteDance-Seed/Seed-OSS-36B-Instruct","parameter_count":"36.2B","parameters_raw":36151104512,"pipeline_tag":"text-generation","provider":"bytedance-seed","quantization":"Q4_K_M","release_date":"2025-08-20","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ByteDance-Seed/Seed-OSS-36B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"}],"hf_downloads":718615,"hf_likes":1503,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":197000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMaxAI/MiniMax-M2.5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen2.5-72B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.59},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-72B-Instruct-GGUF"}],"hf_downloads":374955,"hf_likes":972,"matched_hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","memory":{"min_ram_gb":40.6,"min_vram_gb":37.2,"recommended_ram_gb":67.7},"model_id":"Qwen/Qwen2.5-72B-Instruct","parameter_count":"72.7B","parameters_raw":72706203648,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-72B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":33000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen2.5-72B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"Qwen/Qwen2.5-7B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-7B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-7B-Instruct-GGUF"}],"hf_downloads":12270820,"hf_likes":1543,"matched_hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","memory":{"min_ram_gb":4.3,"min_vram_gb":3.9,"recommended_ram_gb":7.1},"model_id":"Qwen/Qwen2.5-7B-Instruct","parameter_count":"7.6B","parameters_raw":7615616512,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-7B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":33000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen2.5-7B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"Qwen/Qwen3-14B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-14B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-14B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-14B-GGUF"}],"hf_downloads":2271204,"hf_likes":440,"matched_hugging_face_id":"Qwen/Qwen3-14B","memory":{"min_ram_gb":8.3,"min_vram_gb":7.6,"recommended_ram_gb":13.8},"model_id":"Qwen/Qwen3-14B","parameter_count":"14.8B","parameters_raw":14768307200,"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":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-14B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-14B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-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":{"input":0.13,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF"}],"hf_downloads":29400,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-235B-A22B-Thinking-2507","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1903290,"hf_likes":827,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-30B-A3B-Instruct-2507","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":6915474,"hf_likes":732,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-32B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","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":{"input":0.06,"output":0.06},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","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":16046227,"hf_likes":1298,"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":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-8B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-8B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Coder-30B-A3B-Instruct-GGUF"}],"hf_downloads":1220581,"hf_likes":1204,"matched_hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-31","source":"llmfit","use_case":"Code generation and completion"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-01","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91107,"hf_likes":1360,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"Qwen/Qwen3-VL-235B-A22B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Instruct-GGUF"}],"hf_downloads":1606214,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-235B-A22B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-04","retired":false,"tags":null},"Qwen/Qwen3-VL-235B-A22B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Thinking-GGUF"}],"hf_downloads":11386,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-235B-A22B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-04","retired":false,"tags":null},"Qwen/Qwen3-VL-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":393070,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-30B-A3B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-05","retired":false,"tags":null},"Qwen/Qwen3-VL-30B-A3B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF"}],"hf_downloads":68408,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-30B-A3B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-11","retired":false,"tags":null},"Qwen/Qwen3-VL-32B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-32B-Instruct-GGUF"}],"hf_downloads":2278684,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","memory":{"min_ram_gb":18.6,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"Qwen/Qwen3-VL-32B-Instruct","parameter_count":"33.4B","parameters_raw":33357390064,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-32B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-32B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-21","retired":false,"tags":null},"Qwen/Qwen3-VL-32B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-32B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-32B-Thinking-GGUF"}],"hf_downloads":13675,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-32B-Thinking","memory":{"min_ram_gb":18.6,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"Qwen/Qwen3-VL-32B-Thinking","parameter_count":"33.4B","parameters_raw":33357390064,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-32B-Thinking","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-32B-Thinking","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-21","retired":false,"tags":null},"Qwen/Qwen3-VL-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.68},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":5098481,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"Qwen/Qwen3-VL-8B-Instruct","parameter_count":"8.8B","parameters_raw":8767123696,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-VL-8B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen/Qwen3-VL-8B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"Qwen/Qwen3.5-122B-A10B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":2.08},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2211510,"hf_likes":606,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2807949,"hf_likes":1028,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-27B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.24,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2397838,"hf_likes":1489,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.39,"output":2.34},"deprecated":false,"extra":{"attachment":false,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":278133,"hf_likes":1552,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-15","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":14256143,"hf_likes":1824,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen/Qwen3.5-9B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-03-03","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6928584,"hf_likes":2266,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"siliconflow","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.6},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5895532,"hf_likes":2697,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"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":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"baidu/ERNIE-4.5-300B-A47B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ernie","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"baidu/ERNIE-4.5-300B-A47B","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"baidu/ERNIE-4.5-300B-A47B","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-02","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":2.18},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":7455596,"hf_likes":13576,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-R1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3-GGUF"}],"hf_downloads":1100153,"hf_likes":4171,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2024-12-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":232218,"hf_likes":826,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1-Terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":19456,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1-Terminus","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.1-Terminus","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1173317,"hf_likes":1467,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":null,"last_updated":"2025-12-03","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.2","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-Exp":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.41},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":146799,"hf_likes":995,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2-Exp","moe":{"active_experts":8,"active_parameters":54617567164,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-Exp","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-ai/DeepSeek-V3.2-Exp","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-10-10","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":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2045206,"hf_likes":2109,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"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":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"siliconflow","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":0.145,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1278742,"hf_likes":5452,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":9990701,"hf_likes":1396,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/gemma-4-31B-it-GGUF"}],"hf_downloads":9704552,"hf_likes":3575,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":17.5,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"google/gemma-4-31B-it","parameter_count":"31.3B","parameters_raw":31273088876,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"inclusionAI/Ling-flash-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","llmfit":{"architecture":"bailing_moe","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"inclusionAI/Ling-flash-2.0","memory":{"min_ram_gb":57.5,"min_vram_gb":52.7,"recommended_ram_gb":95.8},"model_id":"inclusionAI/Ling-flash-2.0","parameter_count":"102.9B","parameters_raw":102889705216,"pipeline_tag":"text-generation","provider":"inclusionai","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"inclusionAI/Ling-flash-2.0","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI/Ling-flash-2.0","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-09-18","retired":false,"tags":null},"moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":808713,"hf_likes":2862,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"moonshotai/Kimi-K2.5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.77,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"moonshotai/Kimi-K2.6","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"openai/gpt-oss-120b","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-13","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.04,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":7966494,"hf_likes":4923,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"openai/gpt-oss-20b","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"stepfun-ai/Step-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":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","llmfit":{"architecture":"step3p5","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/Step-3.5-Flash-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Step-3.5-Flash-GGUF"}],"hf_downloads":162700,"hf_likes":834,"matched_hugging_face_id":"stepfun-ai/Step-3.5-Flash","memory":{"min_ram_gb":111.4,"min_vram_gb":102.1,"recommended_ram_gb":185.7},"model_id":"stepfun-ai/Step-3.5-Flash","parameter_count":"199.4B","parameters_raw":199384301376,"pipeline_tag":"text-generation","provider":"stepfun-ai","quantization":"Q4_K_M","release_date":"2026-02-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"stepfun-ai/Step-3.5-Flash","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"stepfun-ai/Step-3.5-Flash","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"tencent/Hunyuan-A13B-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":{"input":0.14,"output":0.57},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","llmfit":{"architecture":"hunyuan_v1_moe","context_length":32768,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Hunyuan-A13B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Hunyuan-A13B-Instruct-GGUF"}],"hf_downloads":44348,"hf_likes":796,"matched_hugging_face_id":"tencent/Hunyuan-A13B-Instruct","memory":{"min_ram_gb":44.9,"min_vram_gb":41.2,"recommended_ram_gb":74.9},"model_id":"tencent/Hunyuan-A13B-Instruct","parameter_count":"80.4B","parameters_raw":80393183232,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2025-06-25","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"tencent/Hunyuan-A13B-Instruct","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"tencent/Hunyuan-A13B-Instruct","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"tencent/Hy3-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":0.029,"input":0.066,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":65004,"hf_likes":304,"matched_hugging_face_id":"tencent/Hy3-preview","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3-preview","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2026-04-13","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"tencent/Hy3-preview","knowledge":null,"last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3 preview","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"zai-org/GLM-4.5-Air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.86},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-Air-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5-Air-GGUF"}],"hf_downloads":248601,"hf_likes":631,"matched_hugging_face_id":"zai-org/GLM-4.5-Air","memory":{"min_ram_gb":61.7,"min_vram_gb":56.6,"recommended_ram_gb":102.9},"model_id":"zai-org/GLM-4.5-Air","moe":{"active_experts":8,"active_parameters":12082527713,"is_moe":true,"num_experts":128},"parameter_count":"110.5B","parameters_raw":110468824832,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.5-Air","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-4.5-Air","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.95,"output":2.55},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":124645,"hf_likes":2122,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":205000,"output":205000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-5","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":0,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":78747,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-08","lifecycle":null,"limits":{"context":205000,"output":205000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"zai-org/GLM-5.1","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-08","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":0,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2705686,"hf_likes":4983,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1049000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai-org/GLM-5V-Turbo":{"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":0.24,"cache_write":0,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"zai-org/GLM-5V-Turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"zai-org/GLM-5V-Turbo","pricing":null,"provider":"siliconflow","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null}},"name":"SiliconFlow","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;