@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/baseten.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://inference.baseten.co/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.baseten.co/inference/model-apis/overview","env":["BASETEN_API_KEY"],"exclude_models":null,"extra":null,"id":"baseten","models":{"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204000,"output":204000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-02-12","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":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","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":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-25","lifecycle":null,"limits":{"context":164000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Flash 0731","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.145,"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":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Pro","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-24","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":0.12,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-12","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-01-30","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":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Ultra","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/Nemotron-120B-A12B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-120B-A12B","knowledge":"2026-02","last_updated":"2026-03-11","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Super","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128072,"output":128072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT 120B","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/inkling-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":200000,"output":200000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-12-22","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":3.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"baseten","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,"input":1.3,"output":4.3},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai-org/GLM-5.2-Fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.21,"input":2.1,"output":6.6},"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"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-Fast","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Baseten","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://inference.baseten.co/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.baseten.co/inference/model-apis/overview","env":["BASETEN_API_KEY"],"exclude_models":null,"extra":null,"id":"baseten","models":{"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"}],"hf_downloads":718615,"hf_likes":1503,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204000,"output":204000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-02-12","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":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":232218,"hf_likes":826,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"status":"deprecated","temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-25","lifecycle":null,"limits":{"context":164000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":1872232,"hf_likes":3464,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Flash 0731","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.145,"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":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"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":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Pro","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.32,"output":3.96},"deprecated":false,"extra":{"attachment":false,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":21873,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","memory":{"min_ram_gb":922.3,"min_vram_gb":845.4,"recommended_ram_gb":1537.1},"model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","moe":{"active_experts":6,"active_parameters":107024475595,"is_moe":true,"num_experts":384},"parameter_count":"1650.5B","parameters_raw":1650497936906,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deepseek V4 Pro 0813","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-08-12","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":0.12,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":808713,"hf_likes":2862,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-12","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-01-30","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":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":568317,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2136775,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Ultra","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/Nemotron-120B-A12B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/Nemotron-120B-A12B","knowledge":"2026-02","last_updated":"2026-03-11","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Super","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128072,"output":128072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT 120B","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/inkling-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1048576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":71289,"hf_likes":2054,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":200000,"output":200000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2025-12-22","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":3.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":124645,"hf_likes":2122,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":"2026-01","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"baseten","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,"input":1.3,"output":4.3},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":78747,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202800,"output":202800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"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":["none","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":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai-org/GLM-5.2-Fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.21,"input":2.1,"output":6.6},"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"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-Fast","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"baseten","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Baseten","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/berget.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.berget.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://api.berget.ai","env":["BERGET_API_KEY"],"exclude_models":null,"extra":null,"id":"berget","models":{"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.275,"output":0.55},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":"2025-12","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["audio","image","text","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":0.99},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":478538,"hf_likes":2936,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2025-04-27","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-04-27","retired":false,"tags":null},"mistralai/Mistral-Medium-3.5-128B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.65,"output":5.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Medium-3.5-128B","knowledge":"2026-04","last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5 128B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"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":0.33,"output":0.33},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","knowledge":"2025-09","last_updated":"2025-10-01","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct 2506","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-10-01","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":0.16,"input":0.83,"output":3.85},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-28","lifecycle":null,"limits":{"context":327680,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-07-27","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":0.22,"output":0.83},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-120B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.77,"output":2.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-12","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.54,"output":4.84},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","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":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Berget.AI","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.berget.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://api.berget.ai","env":["BERGET_API_KEY"],"exclude_models":null,"extra":null,"id":"berget","models":{"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.275,"output":0.55},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/gemma-4-31B-it-GGUF"}],"hf_downloads":9704552,"hf_likes":3575,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":17.5,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"google/gemma-4-31B-it","parameter_count":"31.3B","parameters_raw":31273088876,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":"2025-12","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["audio","image","text","video"],"output":["text"]},"model":null,"name":"Gemma 4 31B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":0.99},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":312172,"hf_likes":2952,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2025-04-27","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-04-27","retired":false,"tags":null},"mistralai/Mistral-Medium-3.5-128B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.65,"output":5.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Medium-3.5-128B","knowledge":"2026-04","last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5 128B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"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":0.33,"output":0.33},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","knowledge":"2025-09","last_updated":"2025-10-01","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct 2506","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-10-01","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":0.16,"input":0.83,"output":3.85},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2136775,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-28","lifecycle":null,"limits":{"context":327680,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-07-27","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":0.22,"output":0.83},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS-120B","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.77,"output":2.75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":71289,"hf_likes":2054,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-12","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.54,"output":4.84},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","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":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"berget","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Berget.AI","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/blueclaw.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://openai.blueclaw.network/v1","catalog_only":true,"config_schema":null,"doc":"https://blueclaw.network","env":["BLUECLAW_API_KEY"],"exclude_models":null,"extra":null,"id":"blueclaw","models":{"Qwen/Qwen3.6-35B-A3B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"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":true,"gguf_sources":[],"hf_downloads":8818827,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B-FP8","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B-FP8","moe":{"active_experts":8,"active_parameters":2865078437,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35953925552,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B-FP8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":196608,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null}},"name":"Blue Claw","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://openai.blueclaw.network/v1","catalog_only":true,"config_schema":null,"doc":"https://blueclaw.network","env":["BLUECLAW_API_KEY"],"exclude_models":null,"extra":null,"id":"blueclaw","models":{"Qwen/Qwen3.6-35B-A3B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"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":true,"gguf_sources":[],"hf_downloads":11633364,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B-FP8","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B-FP8","moe":{"active_experts":8,"active_parameters":2865078437,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35953925552,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B-FP8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":196608,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"blueclaw","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null}},"name":"Blue Claw","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/chutes.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "chutes",
-  "Nemotron-3-Nano-Omni-30B-TEE" | "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE" | "Qwen/Qwen3-32B-TEE" | "Qwen/Qwen3.5-397B-A17B-TEE" | "Qwen/Qwen3.6-27B-TEE" | "deepseek-ai/DeepSeek-V3.2-TEE" | "deepseek-ai/DeepSeek-V4-Flash-0731-TEE" | "google/gemma-4-31B-turbo-TEE" | "moonshotai/Kimi-K2.6-TEE" | "moonshotai/Kimi-K3-TEE" | "unsloth/Mistral-Nemo-Instruct-2407-TEE" | "zai-org/GLM-5.1-TEE" | "zai-org/GLM-5.2-TEE"
+  "Nemotron-3-Nano-Omni-30B-TEE" | "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE" | "Qwen/Qwen3-32B-TEE" | "Qwen/Qwen3.5-397B-A17B-TEE" | "Qwen/Qwen3.6-27B-TEE" | "Qwen/Qwen3.8-27B-TEE" | "deepseek-ai/DeepSeek-V3.2-TEE" | "deepseek-ai/DeepSeek-V4-Flash-0731-TEE" | "google/gemma-4-31B-turbo-TEE" | "moonshotai/Kimi-K2.6-TEE" | "moonshotai/Kimi-K3-TEE" | "unsloth/Mistral-Nemo-Instruct-2407-TEE" | "zai-org/GLM-5.1-TEE" | "zai-org/GLM-5.2-TEE"
 >;
 export default provider;

package/dist/providers/chutes.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://llm.chutes.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://llm.chutes.ai/v1/models","env":["CHUTES_API_KEY"],"exclude_models":null,"extra":null,"id":"chutes","models":{"Nemotron-3-Nano-Omni-30B-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","open_weights":true,"temperature":true},"family":null,"id":"Nemotron-3-Nano-Omni-30B-TEE","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni 30B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE":{"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":0.029889999999999993,"input":0.2989,"output":1.1957},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","knowledge":"2025-04","last_updated":"2026-06-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking 2507 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-07","retired":false,"tags":null},"Qwen/Qwen3-32B-TEE":{"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":0.010399999999999998,"input":0.104,"output":0.416},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B-TEE","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-TEE":{"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":0.04499999999999999,"input":0.45,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-TEE","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B A17B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen3.6-27B-TEE":{"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":0.029999999999999992,"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B-TEE","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-TEE":{"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":0.09999999999999998,"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-TEE","knowledge":null,"last_updated":"2026-06-21","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731-TEE":{"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":0.013999999999999999,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","knowledge":"2025-05","last_updated":"2026-08-02","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"google/gemma-4-31B-turbo-TEE":{"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":0.011999999999999997,"input":0.12,"output":0.37},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-turbo-TEE","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gemma 4 31B turbo TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"moonshotai/Kimi-K2.6-TEE":{"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":0.05799999999999998,"input":0.58,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6-TEE","knowledge":"2025-12","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K3-TEE":{"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":0.29999999999999993,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3-TEE","knowledge":null,"last_updated":"2026-07-29","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"unsloth/Mistral-Nemo-Instruct-2407-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","open_weights":true,"temperature":true},"family":null,"id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct 2407 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"zai-org/GLM-5.1-TEE":{"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":0.09799999999999998,"input":0.98,"output":3.08},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1-TEE","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2-TEE":{"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":0.12499999999999997,"input":1.25,"output":3.95},"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"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-TEE","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Chutes","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://llm.chutes.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://llm.chutes.ai/v1/models","env":["CHUTES_API_KEY"],"exclude_models":null,"extra":null,"id":"chutes","models":{"Nemotron-3-Nano-Omni-30B-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","open_weights":true,"temperature":true},"family":null,"id":"Nemotron-3-Nano-Omni-30B-TEE","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni 30B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE":{"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":0.029889999999999993,"input":0.2989,"output":1.1957},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","knowledge":"2025-04","last_updated":"2026-06-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking 2507 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-07","retired":false,"tags":null},"Qwen/Qwen3-32B-TEE":{"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":0.010399999999999998,"input":0.104,"output":0.416},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B-TEE","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-TEE":{"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":0.04499999999999999,"input":0.45,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-TEE","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B A17B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen3.6-27B-TEE":{"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":0.029999999999999992,"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B-TEE","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen/Qwen3.8-27B-TEE":{"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":0.039999999999999994,"input":0.4,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.8-27B-TEE","knowledge":null,"last_updated":"2026-08-16","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.8 27B TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-08-16","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-TEE":{"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":0.09999999999999998,"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-TEE","knowledge":"2024-07","last_updated":"2026-06-21","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731-TEE":{"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":0.013999999999999999,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","knowledge":"2025-05","last_updated":"2026-08-02","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"google/gemma-4-31B-turbo-TEE":{"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":0.011999999999999997,"input":0.12,"output":0.37},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-turbo-TEE","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gemma 4 31B turbo TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"moonshotai/Kimi-K2.6-TEE":{"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":0.05799999999999998,"input":0.58,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6-TEE","knowledge":"2025-12","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K3-TEE":{"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":0.29999999999999993,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3-TEE","knowledge":null,"last_updated":"2026-07-29","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"unsloth/Mistral-Nemo-Instruct-2407-TEE":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.0024499999999999995,"input":0.0245,"output":0.0978},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","open_weights":true,"temperature":true},"family":null,"id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct 2407 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"zai-org/GLM-5.1-TEE":{"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":0.09799999999999998,"input":0.98,"output":3.08},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1-TEE","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2-TEE":{"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":0.12499999999999997,"input":1.25,"output":3.95},"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"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-TEE","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 TEE","pricing":null,"provider":"chutes","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Chutes","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/clarifai.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.clarifai.com/v2/ext/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.clarifai.com/compute/inference/","env":["CLARIFAI_PAT"],"exclude_models":null,"extra":null,"id":"clarifai","models":{"arcee_ai/AFM/models/trinity-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.045,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"trinity-mini","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"arcee_ai/AFM/models/trinity-mini","knowledge":"2024-10","last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trinity Mini","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"clarifai/main/models/mm-poly-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.658,"output":1.11},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","open_weights":false,"temperature":true},"family":null,"id":"clarifai/main/models/mm-poly-8b","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":32768,"output":4096},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MM Poly 8B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-06","retired":false,"tags":null},"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.7},"deprecated":false,"extra":{"attachment":true,"description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek OCR","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-10-20","retired":false,"tags":null},"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5 High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-14B-Reasoning-2512":{"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":2.5,"output":1.7},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","knowledge":"2025-12","last_updated":"2025-12-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-3B-Reasoning-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.039,"output":0.54825},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 3B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"moonshotai/chat-completion/models/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":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/chat-completion/models/Kimi-K2_6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-120b-high-throughput":{"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":0.09,"output":0.36},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.045,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-20b","knowledge":null,"last_updated":"2025-12-12","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwenCoder/models/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":0.11458,"output":0.74812},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","knowledge":"2025-04","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30B A3B Instruct","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"qwen/qwenLM/models/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":0.3,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"qwen/qwenLM/models/Qwen3-30B-A3B-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":0.36,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Thinking 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null}},"name":"Clarifai","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.clarifai.com/v2/ext/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.clarifai.com/compute/inference/","env":["CLARIFAI_PAT"],"exclude_models":null,"extra":null,"id":"clarifai","models":{"arcee_ai/AFM/models/trinity-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.045,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads","family":"trinity","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"arcee_ai/AFM/models/trinity-mini","knowledge":"2024-10","last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trinity Mini","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"clarifai/main/models/mm-poly-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.658,"output":1.11},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","open_weights":false,"temperature":true},"family":null,"id":"clarifai/main/models/mm-poly-8b","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":32768,"output":4096},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MM Poly 8B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-06","retired":false,"tags":null},"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.7},"deprecated":false,"extra":{"attachment":true,"description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek OCR","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-10-20","retired":false,"tags":null},"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5 High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-14B-Reasoning-2512":{"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":2.5,"output":1.7},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","knowledge":"2025-12","last_updated":"2025-12-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"mistralai/completion/models/Ministral-3-3B-Reasoning-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.039,"output":0.54825},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 3B Reasoning 2512","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-12","retired":false,"tags":null},"moonshotai/chat-completion/models/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":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/chat-completion/models/Kimi-K2_6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-120b-high-throughput":{"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":0.09,"output":0.36},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B High Throughput","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/chat-completion/models/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.045,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/chat-completion/models/gpt-oss-20b","knowledge":null,"last_updated":"2025-12-12","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwenCoder/models/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":0.11458,"output":0.74812},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","knowledge":"2025-04","last_updated":"2026-02-12","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30B A3B Instruct","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"qwen/qwenLM/models/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":0.3,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"qwen/qwenLM/models/Qwen3-30B-A3B-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":0.36,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Thinking 2507","pricing":null,"provider":"clarifai","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null}},"name":"Clarifai","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;