@agentjido/llmdb 2026.8.2

package/dist/providers/io_net.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.intelligence.io.solutions/api/v1","catalog_only":true,"config_schema":null,"doc":"https://io.net/docs/guides/intelligence/io-intelligence","env":["IOINTELLIGENCE_API_KEY"],"exclude_models":null,"extra":null,"id":"io_net","models":{"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"cache_write":0.44,"input":0.22,"output":0.95},"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":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","knowledge":"2024-12","last_updated":"2025-01-15","lifecycle":null,"limits":{"context":106000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Coder 480B","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"Qwen/Qwen2.5-VL-32B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.1,"input":0.05,"output":0.22},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-VL-32B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen2.5-VL-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-VL-32B-Instruct-GGUF"}],"hf_downloads":1072669,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen2.5-VL-32B-Instruct","memory":{"min_ram_gb":18.7,"min_vram_gb":17.1,"recommended_ram_gb":31.2},"model_id":"Qwen/Qwen2.5-VL-32B-Instruct","parameter_count":"33.5B","parameters_raw":33452718336,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-VL-32B-Instruct","knowledge":"2024-09","last_updated":"2024-11-01","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 2.5 VL 32B Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.055,"cache_write":0.22,"input":0.11,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF"}],"hf_downloads":29970,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","knowledge":"2024-12","last_updated":"2025-07-01","lifecycle":null,"limits":{"context":262144,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 235B Thinking","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.2,"input":0.1,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Instruct-GGUF"}],"hf_downloads":285987,"hf_likes":1042,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","knowledge":"2024-12","last_updated":"2025-01-10","lifecycle":null,"limits":{"context":262144,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Next 80B Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-01-10","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":4,"input":2,"output":8.75},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":206900,"hf_likes":2457,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1-0528","knowledge":"2024-07","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"meta-llama/Llama-3.2-90B-Vision-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"cache_write":0.7,"input":0.35,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","llmfit":{"architecture":"mllama","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":125847,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-3.2-90B-Vision-Instruct","memory":{"min_ram_gb":49.5,"min_vram_gb":45.4,"recommended_ram_gb":82.5},"model_id":"meta-llama/Llama-3.2-90B-Vision-Instruct","parameter_count":"88.6B","parameters_raw":88593355323,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.2-90B-Vision-Instruct","knowledge":"2023-12","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":16000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 3.2 90B Vision Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.065,"cache_write":0.26,"input":0.13,"output":0.38},"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,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.3,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":117872,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.1},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","moe":{"active_experts":1,"active_parameters":43930451431,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401649841664,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","knowledge":"2024-12","last_updated":"2025-01-15","lifecycle":null,"limits":{"context":430000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B 128E Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"mistralai/Devstral-Small-2505":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.1,"input":0.05,"output":0.22},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","open_weights":false,"temperature":true},"family":null,"id":"mistralai/Devstral-Small-2505","knowledge":"2024-12","last_updated":"2025-05-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral Small 2505","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-05-01","retired":false,"tags":null},"mistralai/Magistral-Small-2506":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":1,"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","open_weights":false,"temperature":true},"family":null,"id":"mistralai/Magistral-Small-2506","knowledge":"2025-01","last_updated":"2025-06-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magistral Small 2506","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"mistralai/Mistral-Large-Instruct-2411":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":4,"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":false,"temperature":true},"family":null,"id":"mistralai/Mistral-Large-Instruct-2411","knowledge":"2024-10","last_updated":"2024-11-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Large Instruct 2411","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistralai/Mistral-Nemo-Instruct-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"cache_write":0.04,"input":0.02,"output":0.04},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Nemo-Instruct-2407","knowledge":"2024-05","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct 2407","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"moonshotai/Kimi-K2-Instruct-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.195,"cache_write":0.78,"input":0.39,"output":1.9},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":66851,"hf_likes":787,"matched_hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","memory":{"min_ram_gb":573.6,"min_vram_gb":525.8,"recommended_ram_gb":956.0},"model_id":"moonshotai/Kimi-K2-Instruct-0905","moe":{"active_experts":8,"active_parameters":71639103404,"is_moe":true,"num_experts":384},"parameter_count":"1026.5B","parameters_raw":1026470735448,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-09-03","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":false,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2-Instruct-0905","knowledge":"2024-08","last_updated":"2024-09-05","lifecycle":null,"limits":{"context":32768,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Instruct","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-09-05","retired":false,"tags":null},"moonshotai/Kimi-K2-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"cache_write":1.1,"input":0.55,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":62805,"hf_likes":1714,"matched_hugging_face_id":"moonshotai/Kimi-K2-Thinking","memory":{"min_ram_gb":591.3,"min_vram_gb":542.0,"recommended_ram_gb":985.4},"model_id":"moonshotai/Kimi-K2-Thinking","moe":{"active_experts":8,"active_parameters":73847838596,"is_moe":true,"num_experts":384},"parameter_count":"1058.1B","parameters_raw":1058118284416,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-11-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2-Thinking","knowledge":"2024-08","last_updated":"2024-11-01","lifecycle":null,"limits":{"context":32768,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-11-01","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":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.08,"input":0.04,"output":0.4},"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,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS 120B","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"cache_write":0.06,"input":0.03,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":64000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-OSS 20B","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.8,"input":0.4,"output":1.75},"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-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2024-10","last_updated":"2024-11-15","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.6","pricing":null,"provider":"io_net","provider_model_id":null,"release_date":"2024-11-15","retired":false,"tags":null}},"name":"IO.NET","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/jiekou.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "jiekou",
+  "baidu/ernie-4.5-300b-a47b-paddle" | "baidu/ernie-4.5-vl-424b-a47b" | "claude-haiku-4-5-20251001" | "claude-opus-4-1-20250805" | "claude-opus-4-20250514" | "claude-opus-4-5-20251101" | "claude-opus-4-6" | "claude-sonnet-4-20250514" | "claude-sonnet-4-5-20250929" | "deepseek/deepseek-r1-0528" | "deepseek/deepseek-v3-0324" | "deepseek/deepseek-v3.1" | "gemini-2.5-flash" | "gemini-2.5-flash-lite" | "gemini-2.5-flash-lite-preview-06-17" | "gemini-2.5-flash-lite-preview-09-2025" | "gemini-2.5-flash-preview-05-20" | "gemini-2.5-pro" | "gemini-2.5-pro-preview-06-05" | "gemini-3-flash-preview" | "gemini-3-pro-preview" | "gpt-5-chat-latest" | "gpt-5-codex" | "gpt-5-mini" | "gpt-5-nano" | "gpt-5-pro" | "gpt-5.1" | "gpt-5.1-codex" | "gpt-5.1-codex-max" | "gpt-5.1-codex-mini" | "gpt-5.2" | "gpt-5.2-codex" | "gpt-5.2-pro" | "grok-4-0709" | "grok-4-1-fast-non-reasoning" | "grok-4-1-fast-reasoning" | "grok-4-fast-non-reasoning" | "grok-4-fast-reasoning" | "grok-code-fast-1" | "minimax/minimax-m2.1" | "minimaxai/minimax-m1-80k" | "moonshotai/kimi-k2-0905" | "moonshotai/kimi-k2-instruct" | "moonshotai/kimi-k2.5" | "o3" | "o3-mini" | "o4-mini" | "qwen/qwen3-235b-a22b-fp8" | "qwen/qwen3-235b-a22b-instruct-2507" | "qwen/qwen3-235b-a22b-thinking-2507" | "qwen/qwen3-30b-a3b-fp8" | "qwen/qwen3-32b-fp8" | "qwen/qwen3-coder-480b-a35b-instruct" | "qwen/qwen3-coder-next" | "qwen/qwen3-next-80b-a3b-instruct" | "qwen/qwen3-next-80b-a3b-thinking" | "xiaomimimo/mimo-v2-flash" | "zai-org/glm-4.5" | "zai-org/glm-4.5v" | "zai-org/glm-4.7" | "zai-org/glm-4.7-flash"
+>;
+export default provider;

package/dist/providers/jiekou.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.jiekou.ai/openai","catalog_only":true,"config_schema":null,"doc":"https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev","env":["JIEKOU_API_KEY"],"exclude_models":null,"extra":null,"id":"jiekou","models":{"baidu/ernie-4.5-300b-a47b-paddle":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ernie","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"baidu/ernie-4.5-300b-a47b-paddle","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":123000,"output":12000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ERNIE 4.5 300B A47B","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"baidu/ernie-4.5-vl-424b-a47b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.42,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-424b-a47b","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":123000,"output":16000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"ERNIE 4.5 VL 424B A47B","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-haiku-4-5-20251001":{"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":0.9,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-haiku-4-5-20251001","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":20000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-haiku-4-5-20251001","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-opus-4-1-20250805":{"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":13.5,"output":67.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-1-20250805","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-opus-4-1-20250805","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-opus-4-20250514":{"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":13.5,"output":67.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-20250514","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-opus-4-20250514","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-opus-4-5-20251101":{"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":4.5,"output":22.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-5-20251101","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-opus-4-5-20251101","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"max":127999,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-02","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-opus-4-6","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-02","retired":false,"tags":null},"claude-sonnet-4-20250514":{"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":2.7,"output":13.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-20250514","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-sonnet-4-20250514","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"claude-sonnet-4-5-20250929":{"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":2.7,"output":13.5},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5-20250929","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"claude-sonnet-4-5-20250929","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"deepseek/deepseek-r1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-0528","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 0528","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"deepseek/deepseek-v3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.14},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3-0324","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"deepseek/deepseek-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"max":32767,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":2.25},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-flash","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash-lite","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-flash-lite","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-flash-lite-preview-06-17":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash-lite-preview-06-17","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","video","image","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-flash-lite-preview-06-17","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-flash-lite-preview-09-2025":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash-lite-preview-09-2025","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-flash-lite-preview-09-2025","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-flash-preview-05-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.135,"output":3.15},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash-preview-05-20","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":200000},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-flash-preview-05-20","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-pro","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-2.5-pro-preview-06-05":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-pro-preview-06-05","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":200000},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-2.5-pro-preview-06-05","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-3-flash-preview":{"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":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-3-flash-preview","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gemini-3-pro-preview":{"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":1.8,"output":10.8},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-pro-preview","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"gemini-3-pro-preview","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5-chat-latest":{"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":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-chat-latest","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5-chat-latest","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5-codex":{"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":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-codex","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5-codex","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.225,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-mini","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5-mini","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.045,"output":0.36},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-nano","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5-nano","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":13.5,"output":108},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-pro","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":272000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5-pro","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.1","knowledge":null,"last_updated":"2026-02","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.1","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-02","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.1-codex","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.1-codex","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.125,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.1-codex-max","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.1-codex-max","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.1-codex-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":0.225,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.1-codex-mini","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.1-codex-mini","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.2":{"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":1.575,"output":12.6},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.2","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.2","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.2-codex","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.2-codex","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"gpt-5.2-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":{"input":18.9,"output":151.2},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.2-pro","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gpt-5.2-pro","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-4-0709":{"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":2.7,"output":13.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-0709","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-4-0709","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.45},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-4-1-fast-non-reasoning","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-4-1-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.45},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-1-fast-reasoning","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-4-1-fast-reasoning","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-4-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.45},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-fast-non-reasoning","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-4-fast-non-reasoning","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-4-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":0.45},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-fast-reasoning","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-4-fast-reasoning","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"grok-code-fast-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.18,"output":1.35},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"grok-code-fast-1","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"grok-code-fast-1","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"minimax/minimax-m2.1":{"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":0.3,"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":[{"max":131071,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.1","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Minimax M2.1","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"minimaxai/minimax-m1-80k":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"minimaxai/minimax-m1-80k","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":1000000,"output":40000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M1","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"moonshotai/kimi-k2-0905":{"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":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-0905","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 0905","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"moonshotai/kimi-k2-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":0.57,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-instruct","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Instruct","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","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":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","open_weights":true,"reasoning_options":[{"max":262143,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"o3":{"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":10,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"o3","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"o3-mini":{"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":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"o3-mini","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"o4-mini":{"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":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"o4-mini","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-235b-a22b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-fp8","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.8},"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/qwen3-235b-a22b-instruct-2507","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":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/qwen3-235b-a22b-thinking-2507","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22b Thinking 2507","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-30b-a3b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.09,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-fp8","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-32b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.1,"output":0.45},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-32b-fp8","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":40960,"output":20000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-coder-480b-a35b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-480b-a35b-instruct","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-next","knowledge":null,"last_updated":"2026-02","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"qwen/qwen3-coder-next","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-02","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.5},"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/qwen3-next-80b-a3b-instruct","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Instruct","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.5},"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/qwen3-next-80b-a3b-thinking","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Thinking","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"xiaomimimo/mimo-v2-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xiaomimimo/mimo-v2-flash","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"XiaomiMiMo/MiMo-V2-Flash","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"zai-org/glm-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.5","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"zai-org/glm-4.5v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.5v","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"GLM 4.5V","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","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":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"zai-org/glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7-flash","knowledge":null,"last_updated":"2026-01","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"jiekou","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null}},"name":"Jiekou.AI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/kenari.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "kenari",
+  "claude-fable-5" | "claude-opus-4-7" | "claude-opus-4-8" | "claude-sonnet-5" | "deepseek-v4-flash" | "deepseek-v4-flash:free" | "deepseek-v4-pro" | "gemini-2-5-flash" | "gemini-2-5-flash-lite" | "gemini-3-1-flash-lite" | "gemma-4-31b-it" | "glm-4-7-flash:free" | "glm-5-1" | "glm-5-2" | "gpt-5-4-mini" | "gpt-5-5" | "gpt-5-6-luna" | "gpt-5-6-sol" | "gpt-5-6-terra" | "gpt-image-2" | "gpt-oss-120b" | "gpt-oss-20b" | "grok-4-5" | "grok-build-0-1" | "kimi-k2-6" | "kimi-k2-6:free" | "kimi-k2-7-code" | "kimi-k2-7-code:free" | "kimi-k3" | "mimo-v2-5" | "mimo-v2-5-pro" | "mimo-v2-5:free" | "minimax-m3" | "nemotron-3-nano-30b-a3b" | "nemotron-3-super-120b-a12b" | "nemotron-3-super-120b-a12b:free" | "nemotron-3-ultra-550b-a55b" | "qwen3-7-plus"
+>;
+export default provider;

package/dist/providers/kenari.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://kenari.id/v1","catalog_only":true,"config_schema":null,"doc":"https://kenari.id/docs","env":["KENARI_API_KEY"],"exclude_models":null,"extra":null,"id":"kenari","models":{"claude-fable-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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-sonnet-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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-v4-flash:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash:free","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"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":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gemini-2-5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2-5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2-5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2-5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3-1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"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,"output":0},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"glm-4-7-flash:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-4-7-flash:free","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"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":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"glm-5-1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"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":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5-2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-5-4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5-6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5-6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5-6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":false},"family":null,"id":"gpt-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":272000,"output":16384},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"GPT-Image-2","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"family":null,"id":"gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"grok-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"grok-build-0-1":{"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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-build-0-1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2-6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2-6:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2-6:free","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6 (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2-7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"kimi-k2-7-code:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-7-code:free","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"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":0,"output":0},"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"mimo-v2-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mimo-v2-5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"mimo-v2-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mimo-v2-5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"mimo-v2-5:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mimo-v2-5:free","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5 (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"minimax-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":512000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"nemotron-3-nano-30b-a3b","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium"]}],"temperature":true},"family":null,"id":"nemotron-3-super-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nemotron-3-super-120b-a12b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium"]}],"temperature":true},"family":null,"id":"nemotron-3-super-120b-a12b:free","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B (Free)","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"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":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["medium","high"]}],"temperature":true},"family":null,"id":"nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"qwen3-7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"kenari","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null}},"name":"Kenari","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/kilo.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "kilo",
+  "ai21/jamba-large-1.7" | "aion-labs/aion-2.0" | "aion-labs/aion-3.0" | "aion-labs/aion-3.0-mini" | "aion-labs/aion-rp-llama-3.1-8b" | "allenai/olmo-3-32b-think" | "amazon/nova-2-lite-v1" | "amazon/nova-lite-v1" | "amazon/nova-micro-v1" | "amazon/nova-premier-v1" | "amazon/nova-pro-v1" | "anthracite-org/magnum-v4-72b" | "anthropic/claude-3-haiku" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4.5" | "anthropic/claude-opus-4" | "anthropic/claude-opus-4.1" | "anthropic/claude-opus-4.5" | "anthropic/claude-opus-4.6" | "anthropic/claude-opus-4.7" | "anthropic/claude-opus-4.7-fast" | "anthropic/claude-opus-4.8" | "anthropic/claude-opus-4.8-fast" | "anthropic/claude-opus-5" | "anthropic/claude-opus-5-fast" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4.5" | "anthropic/claude-sonnet-4.6" | "anthropic/claude-sonnet-5" | "arcee-ai/trinity-large-thinking" | "arcee-ai/virtuoso-large" | "baidu/ernie-4.5-vl-424b-a47b" | "bytedance-seed/seed-1.6" | "bytedance-seed/seed-1.6-flash" | "bytedance-seed/seed-2.0-lite" | "bytedance-seed/seed-2.0-mini" | "bytedance/ui-tars-1.5-7b" | "cognitivecomputations/dolphin-mistral-24b-venice-edition" | "cohere/command-a" | "cohere/command-r-08-2024" | "cohere/command-r-plus-08-2024" | "cohere/command-r7b-12-2024" | "cohere/north-mini-code:free" | "deepcogito/cogito-v2.1-671b" | "deepseek/deepseek-chat" | "deepseek/deepseek-chat-v3-0324" | "deepseek/deepseek-chat-v3.1" | "deepseek/deepseek-r1" | "deepseek/deepseek-r1-0528" | "deepseek/deepseek-r1-distill-llama-70b" | "deepseek/deepseek-v3.1-terminus" | "deepseek/deepseek-v3.2" | "deepseek/deepseek-v3.2-exp" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-flash-0731" | "deepseek/deepseek-v4-flash:discounted" | "deepseek/deepseek-v4-pro" | "deepseek/deepseek-v4-pro:discounted" | "google/gemini-2.5-flash" | "google/gemini-2.5-flash-image" | "google/gemini-2.5-flash-lite" | "google/gemini-2.5-pro" | "google/gemini-2.5-pro-preview" | "google/gemini-2.5-pro-preview-05-06" | "google/gemini-3-flash-preview" | "google/gemini-3-pro-image" | "google/gemini-3-pro-image-preview" | "google/gemini-3.1-flash-image" | "google/gemini-3.1-flash-image-preview" | "google/gemini-3.1-flash-lite" | "google/gemini-3.1-flash-lite-image" | "google/gemini-3.1-flash-lite-preview" | "google/gemini-3.1-pro-preview" | "google/gemini-3.1-pro-preview-customtools" | "google/gemini-3.5-flash" | "google/gemini-3.5-flash-lite" | "google/gemini-3.6-flash" | "google/gemma-2-27b-it" | "google/gemma-3-12b-it" | "google/gemma-3-27b-it" | "google/gemma-3-4b-it" | "google/gemma-3n-e4b-it" | "google/gemma-4-26b-a4b-it" | "google/gemma-4-31b-it" | "google/lyria-3-clip-preview" | "google/lyria-3-pro-preview" | "gryphe/mythomax-l2-13b" | "ibm-granite/granite-4.0-h-micro" | "ibm-granite/granite-4.1-8b" | "inception/mercury-2" | "inclusionai/ling-2.6-1t" | "inclusionai/ling-2.6-flash" | "inclusionai/ling-3.0-flash:free" | "inclusionai/ring-2.6-1t" | "kilo-auto/balanced" | "kilo-auto/efficient" | "kilo-auto/free" | "kilo-auto/frontier" | "kilo-auto/small" | "kwaipilot/kat-coder-air-v2.5" | "kwaipilot/kat-coder-pro-v2" | "kwaipilot/kat-coder-pro-v2.5" | "mancer/weaver" | "meituan/longcat-2.0" | "meta-llama/llama-3.1-70b-instruct" | "meta-llama/llama-3.1-8b-instruct" | "meta-llama/llama-3.2-1b-instruct" | "meta-llama/llama-3.2-3b-instruct" | "meta-llama/llama-3.3-70b-instruct" | "meta-llama/llama-4-maverick" | "meta-llama/llama-4-scout" | "meta-llama/llama-guard-4-12b" | "meta/muse-spark-1.1" | "microsoft/phi-4" | "microsoft/wizardlm-2-8x22b" | "minimax/minimax-01" | "minimax/minimax-m1" | "minimax/minimax-m2" | "minimax/minimax-m2-her" | "minimax/minimax-m2.1" | "minimax/minimax-m2.5" | "minimax/minimax-m2.7" | "minimax/minimax-m3" | "mistralai/codestral-2508" | "mistralai/ministral-14b-2512" | "mistralai/ministral-3b-2512" | "mistralai/ministral-8b-2512" | "mistralai/mistral-large" | "mistralai/mistral-large-2407" | "mistralai/mistral-large-2512" | "mistralai/mistral-medium-3" | "mistralai/mistral-medium-3-5" | "mistralai/mistral-medium-3.1" | "mistralai/mistral-nemo" | "mistralai/mistral-saba" | "mistralai/mistral-small-24b-instruct-2501" | "mistralai/mistral-small-2603" | "mistralai/mistral-small-3.1-24b-instruct" | "mistralai/mistral-small-3.2-24b-instruct" | "mistralai/mixtral-8x22b-instruct" | "mistralai/voxtral-small-24b-2507" | "moonshotai/kimi-k2" | "moonshotai/kimi-k2-0905" | "moonshotai/kimi-k2-thinking" | "moonshotai/kimi-k2.5" | "moonshotai/kimi-k2.6" | "moonshotai/kimi-k2.7-code" | "moonshotai/kimi-k3" | "morph/morph-v3-fast" | "morph/morph-v3-large" | "nex-agi/nex-n2-mini" | "nex-agi/nex-n2-pro" | "nousresearch/hermes-3-llama-3.1-405b" | "nousresearch/hermes-3-llama-3.1-70b" | "nousresearch/hermes-4-405b" | "nousresearch/hermes-4-70b" | "nvidia/nemotron-3-nano-30b-a3b" | "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" | "nvidia/nemotron-3-super-120b-a12b" | "nvidia/nemotron-3-super-120b-a12b:free" | "nvidia/nemotron-3-ultra-550b-a55b" | "nvidia/nemotron-3-ultra-550b-a55b:free" | "nvidia/nemotron-3.5-content-safety:free" | "openai/gpt-3.5-turbo" | "openai/gpt-3.5-turbo-0613" | "openai/gpt-3.5-turbo-16k" | "openai/gpt-3.5-turbo-instruct" | "openai/gpt-4" | "openai/gpt-4-turbo" | "openai/gpt-4-turbo-preview" | "openai/gpt-4.1" | "openai/gpt-4.1-mini" | "openai/gpt-4.1-nano" | "openai/gpt-4o" | "openai/gpt-4o-2024-05-13" | "openai/gpt-4o-2024-08-06" | "openai/gpt-4o-2024-11-20" | "openai/gpt-4o-mini" | "openai/gpt-4o-mini-2024-07-18" | "openai/gpt-5" | "openai/gpt-5-image" | "openai/gpt-5-image-mini" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5-pro" | "openai/gpt-5.1" | "openai/gpt-5.1-codex" | "openai/gpt-5.1-codex-max" | "openai/gpt-5.1-codex-mini" | "openai/gpt-5.2" | "openai/gpt-5.2-chat" | "openai/gpt-5.2-codex" | "openai/gpt-5.2-pro" | "openai/gpt-5.3-chat" | "openai/gpt-5.3-codex" | "openai/gpt-5.4" | "openai/gpt-5.4-image-2" | "openai/gpt-5.4-mini" | "openai/gpt-5.4-nano" | "openai/gpt-5.4-pro" | "openai/gpt-5.5" | "openai/gpt-5.5-pro" | "openai/gpt-5.6-luna" | "openai/gpt-5.6-luna-pro" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-sol-pro" | "openai/gpt-5.6-terra" | "openai/gpt-5.6-terra-pro" | "openai/gpt-audio" | "openai/gpt-audio-mini" | "openai/gpt-chat-latest" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "openai/gpt-oss-safeguard-20b" | "openai/o1" | "openai/o1-pro" | "openai/o3" | "openai/o3-mini" | "openai/o3-mini-high" | "openai/o3-pro" | "openai/o4-mini" | "openai/o4-mini-high" | "openrouter/auto" | "openrouter/bodybuilder" | "openrouter/free" | "openrouter/pareto-code" | "perceptron/perceptron-mk1" | "perplexity/sonar" | "perplexity/sonar-deep-research" | "perplexity/sonar-pro" | "perplexity/sonar-pro-search" | "perplexity/sonar-reasoning-pro" | "poolside/laguna-s-2.1" | "poolside/laguna-s-2.1:free" | "poolside/laguna-xs-2.1" | "poolside/laguna-xs-2.1:free" | "qwen/qwen-2.5-72b-instruct" | "qwen/qwen-2.5-7b-instruct" | "qwen/qwen-2.5-coder-32b-instruct" | "qwen/qwen-plus" | "qwen/qwen-plus-2025-07-28" | "qwen/qwen-plus-2025-07-28:thinking" | "qwen/qwen2.5-vl-72b-instruct" | "qwen/qwen3-14b" | "qwen/qwen3-235b-a22b" | "qwen/qwen3-235b-a22b-2507" | "qwen/qwen3-235b-a22b-thinking-2507" | "qwen/qwen3-30b-a3b" | "qwen/qwen3-30b-a3b-instruct-2507" | "qwen/qwen3-30b-a3b-thinking-2507" | "qwen/qwen3-32b" | "qwen/qwen3-8b" | "qwen/qwen3-coder" | "qwen/qwen3-coder-30b-a3b-instruct" | "qwen/qwen3-coder-flash" | "qwen/qwen3-coder-next" | "qwen/qwen3-coder-plus" | "qwen/qwen3-max" | "qwen/qwen3-max-thinking" | "qwen/qwen3-next-80b-a3b-instruct" | "qwen/qwen3-next-80b-a3b-thinking" | "qwen/qwen3-vl-235b-a22b-instruct" | "qwen/qwen3-vl-235b-a22b-thinking" | "qwen/qwen3-vl-30b-a3b-instruct" | "qwen/qwen3-vl-30b-a3b-thinking" | "qwen/qwen3-vl-32b-instruct" | "qwen/qwen3-vl-8b-instruct" | "qwen/qwen3-vl-8b-thinking" | "qwen/qwen3.5-122b-a10b" | "qwen/qwen3.5-27b" | "qwen/qwen3.5-35b-a3b" | "qwen/qwen3.5-397b-a17b" | "qwen/qwen3.5-9b" | "qwen/qwen3.5-flash-02-23" | "qwen/qwen3.5-plus-02-15" | "qwen/qwen3.5-plus-20260420" | "qwen/qwen3.6-27b" | "qwen/qwen3.6-35b-a3b" | "qwen/qwen3.6-flash" | "qwen/qwen3.6-max-preview" | "qwen/qwen3.6-plus" | "qwen/qwen3.7-flash" | "qwen/qwen3.7-max" | "qwen/qwen3.7-plus" | "qwen/qwen3.8-max" | "rekaai/reka-edge" | "rekaai/reka-flash-3" | "relace/relace-apply-3" | "relace/relace-search" | "sakana/fugu-ultra" | "sao10k/l3-lunaris-8b" | "sao10k/l3.1-euryale-70b" | "sao10k/l3.3-euryale-70b" | "stealth/claude-opus-4.6" | "stealth/claude-opus-4.7" | "stealth/claude-opus-4.8" | "stealth/claude-sonnet-4.6" | "stealth/gpt-5.6-sol" | "stealth/qwen3.6-plus" | "stepfun/step-3.5-flash" | "stepfun/step-3.7-flash" | "stepfun/step-3.7-flash:free" | "tencent/hunyuan-a13b-instruct" | "tencent/hy3" | "tencent/hy3-preview" | "tencent/hy3:free" | "thedrummer/cydonia-24b-v4.1" | "thedrummer/rocinante-12b" | "thedrummer/skyfall-36b-v2" | "thedrummer/unslopnemo-12b" | "thinkingmachines/inkling" | "thinkingmachines/inkling-small" | "undi95/remm-slerp-l2-13b" | "upstage/solar-pro-3" | "writer/palmyra-x5" | "x-ai/grok-4.20" | "x-ai/grok-4.20-multi-agent" | "x-ai/grok-4.3" | "x-ai/grok-4.5" | "x-ai/grok-build-0.1" | "xiaomi/mimo-v2.5" | "xiaomi/mimo-v2.5-pro" | "z-ai/glm-4.5" | "z-ai/glm-4.5-air" | "z-ai/glm-4.5v" | "z-ai/glm-4.6" | "z-ai/glm-4.6v" | "z-ai/glm-4.7" | "z-ai/glm-4.7-flash" | "z-ai/glm-5" | "z-ai/glm-5-turbo" | "z-ai/glm-5.1" | "z-ai/glm-5.2" | "z-ai/glm-5v-turbo" | "~anthropic/claude-fable-latest" | "~anthropic/claude-haiku-latest" | "~anthropic/claude-opus-latest" | "~anthropic/claude-sonnet-latest" | "~deepseek/deepseek-v4-flash-latest" | "~google/gemini-flash-latest" | "~google/gemini-pro-latest" | "~moonshotai/kimi-latest" | "~openai/gpt-latest" | "~openai/gpt-mini-latest" | "~x-ai/grok-latest"
+>;
+export default provider;