@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/inceptron.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.inceptron.io/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.inceptron.io","env":["INCEPTRON_API_KEY"],"exclude_models":null,"extra":null,"id":"inceptron","models":{"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0,"input":0.15,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196608,"output":196608},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0,"input":0.66,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.6-Fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"cache_write":0,"input":1.32,"output":7},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"status":"alpha","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6-Fast","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Fast","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0,"input":0.75,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"zai-org/GLM-5.1-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":0,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":494825,"hf_likes":119,"matched_hugging_face_id":"zai-org/GLM-5.1-FP8","memory":{"min_ram_gb":421.3,"min_vram_gb":386.2,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1-FP8","moe":{"active_experts":8,"active_parameters":60077205033,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753910024032,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1-FP8","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":202752},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":0,"input":1.2,"output":4.2},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Inceptron","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.inceptron.io/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.inceptron.io","env":["INCEPTRON_API_KEY"],"exclude_models":null,"extra":null,"id":"inceptron","models":{"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0,"input":0.22,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"}],"hf_downloads":718615,"hf_likes":1503,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196608,"output":196608},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0,"input":0.13,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":1872232,"hf_likes":3464,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0,"input":0.6,"output":3.41},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshotai/Kimi-K2.7-Code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.17,"cache_write":0,"input":0.67,"output":3.4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":568317,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.17,"cache_write":0,"input":0.75,"output":2.9},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2705686,"hf_likes":4983,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"inceptron","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Inceptron","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/inferx.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "inferx",
-  "google/gemma-4-31b-it-fp8" | "qwen/qwen3.5-122b-a10b-nvfp4" | "qwen/qwen3.6-27b-fp8" | "qwen/qwen3.6-35b-a3b-fp8" | "qwen3-coder-next-fp8" | "qwen3-coder-next-fp8-1m"
+  "Agents-A1" | "Devstral-2-123B-Instruct-2512-int4-AutoRound" | "Ornith-1.0-35B-FP8" | "Qwen3-Coder-Next-FP8" | "Qwen3-Coder-Next-FP8-no-thinking" | "Qwen3-Embedding-8B" | "Qwen3.6-27B-FP8" | "Qwen3.6-35B-A3B-FP8" | "Qwen3.6-35B-A3B-fp8-no-thinking" | "deepseek-v4-flash" | "gemma-4-31B-it-fp8" | "mimo-v25"
 >;
 export default provider;

package/dist/providers/inferx.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://model.inferx.net/endpoints/v1","catalog_only":true,"config_schema":null,"doc":"https://model.inferx.net/endpoints","env":["INFERX_API_KEY"],"exclude_models":null,"extra":null,"id":"inferx","models":{"google/gemma-4-31b-it-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it-fp8","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 FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b-nvfp4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b-nvfp4","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":256144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 122B A10B NVFP4","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen/qwen3.6-27b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b-fp8","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"qwen/qwen3.6-35b-a3b-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-35b-a3b-fp8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"qwen3-coder-next-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":{"input":0,"output":0},"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":"qwen3-coder-next-fp8","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":256144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"qwen3-coder-next-fp8-1m":{"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,"output":0},"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":"qwen3-coder-next-fp8-1m","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":1024000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next FP8 1M","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null}},"name":"InferX","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://model.inferx.net/endpoints/v1","catalog_only":true,"config_schema":null,"doc":"https://model.inferx.net/endpoints","env":["INFERX_API_KEY"],"exclude_models":null,"extra":null,"id":"inferx","models":{"Agents-A1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"35B MoE agentic model built for long-horizon search, engineering, and scientific reasoning tasks","open_weights":true,"reasoning_options":[]},"family":null,"id":"Agents-A1","knowledge":null,"last_updated":"2026-06-26","lifecycle":null,"limits":{"context":262000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Agents-A1","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-06-26","retired":false,"tags":null},"Devstral-2-123B-Instruct-2512-int4-AutoRound":{"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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","open_weights":true,"temperature":true},"family":null,"id":"Devstral-2-123B-Instruct-2512-int4-AutoRound","knowledge":"2025-12","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"Ornith-1.0-35B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Large coding-reasoning model for agentic software tasks and RL search","family":"ornith","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Ornith-1.0-35B-FP8","knowledge":null,"last_updated":"2026-06-25","lifecycle":null,"limits":{"context":262000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ornith-1.0-35B-FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-06-25","retired":false,"tags":null},"Qwen3-Coder-Next-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":{"input":0,"output":0},"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":"Qwen3-Coder-Next-FP8","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":256144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"Qwen3-Coder-Next-FP8-no-thinking":{"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,"output":0},"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":"Qwen3-Coder-Next-FP8-no-thinking","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":260000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-Next-FP8-no-thinking","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"Qwen3-Embedding-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"Qwen3-Embedding-8B","knowledge":null,"last_updated":"2025-06-05","lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Embedding-8B","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2025-06-05","retired":false,"tags":null},"Qwen3.6-27B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-27B-FP8","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen3.6-35B-A3B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-35B-A3B-FP8","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"Qwen3.6-35B-A3B-fp8-no-thinking":{"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,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.6-35B-A3B-fp8 disable thinking","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen3.6-35B-A3B-fp8-no-thinking","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6-35B-A3B-fp8-no-thinking","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-17","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":"toggle"}],"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":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"deepseek-v4-flash","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gemma-4-31B-it-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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-fp8","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 FP8","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"mimo-v25":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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-v25","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1000000,"output":100000},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"mimo-v25","pricing":null,"provider":"inferx","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null}},"name":"InferX","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/infomaniak.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://www.infomaniak.com/en/hosting/ai-services/open-source-models","env":["INFOMANIAK_API_KEY","INFOMANIAK_PRODUCT_ID"],"exclude_models":null,"extra":null,"id":"infomaniak","models":{"Qwen/Qwen3.5-122B-A10B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":3.97},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":1257096,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B-FP8","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B-FP8","moe":{"active_experts":8,"active_parameters":9968428637,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125094006512,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":4.46},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-FP8-GGUF"}],"hf_downloads":832304,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B-FP8","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B-FP8","moe":{"active_experts":10,"active_parameters":27656495656,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403422386928,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"bge_multilingual_gemma2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.08,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"bge_multilingual_gemma2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":8000,"output":3584},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Multilingual Gemma2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2024-07-25","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"mini_lm_l12_v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"mini_lm_l12_v2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":128,"output":384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"All-MiniLM-L12-v2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2021-08-30","retired":false,"tags":null},"mistralai/Ministral-3-14B-Instruct-2512":{"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":0.37,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"mistralai/Ministral-3-14B-Instruct-2512","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":25600},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Instruct","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/Mistral-Small-4-119B-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.93},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","interleaved":true,"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/Mistral-Small-4-119B-2603","knowledge":"2025-06","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.74,"output":3.72},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":true,"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-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":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","interleaved":true,"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":606279,"hf_likes":355,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","moe":{"active_experts":6,"active_parameters":2985102726,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577946256,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1000000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"swiss-ai/Apertus-v1.5-70B":{"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":0.87,"output":3.1},"deprecated":false,"extra":{"attachment":true,"description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","open_weights":true,"status":"beta","temperature":true},"family":null,"id":"swiss-ai/Apertus-v1.5-70B","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":8192},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Apertus v1.5 70B","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null}},"name":"Infomaniak","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v1","catalog_only":true,"config_schema":null,"doc":"https://www.infomaniak.com/en/hosting/ai-services/open-source-models","env":["INFOMANIAK_API_KEY","INFOMANIAK_PRODUCT_ID"],"exclude_models":null,"extra":null,"id":"infomaniak","models":{"Qwen/Qwen3.5-122B-A10B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":3.97},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":1712813,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B-FP8","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B-FP8","moe":{"active_experts":8,"active_parameters":9968428637,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125094006512,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.99,"output":4.46},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","interleaved":true,"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-FP8-GGUF"}],"hf_downloads":896814,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B-FP8","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B-FP8","moe":{"active_experts":10,"active_parameters":27656495656,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403422386928,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":200000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"bge_multilingual_gemma2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.08,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"bge_multilingual_gemma2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":8000,"output":3584},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"BGE Multilingual Gemma2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2024-07-25","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/gemma-4-31B-it-GGUF"}],"hf_downloads":9704552,"hf_likes":3575,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":17.5,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"google/gemma-4-31B-it","parameter_count":"31.3B","parameters_raw":31273088876,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"mini_lm_l12_v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":true,"temperature":false},"family":null,"id":"mini_lm_l12_v2","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":128,"output":384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"All-MiniLM-L12-v2","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2021-08-30","retired":false,"tags":null},"mistralai/Ministral-3-14B-Instruct-2512":{"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":0.37,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"mistralai/Ministral-3-14B-Instruct-2512","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":25600},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3 14B Instruct","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/Mistral-Small-4-119B-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.93},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","interleaved":true,"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistralai/Mistral-Small-4-119B-2603","knowledge":"2025-06","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.74,"output":3.72},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":true,"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Nano-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":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","interleaved":true,"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":622594,"hf_likes":357,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","moe":{"active_experts":6,"active_parameters":2985102726,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577946256,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1000000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B FP8","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"swiss-ai/Apertus-v1.5-70B":{"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":0.87,"output":3.1},"deprecated":false,"extra":{"attachment":true,"description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","open_weights":true,"status":"beta","temperature":true},"family":null,"id":"swiss-ai/Apertus-v1.5-70B","knowledge":null,"last_updated":"2026-08-01","lifecycle":null,"limits":{"context":100000,"output":8192},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Apertus v1.5 70B","pricing":null,"provider":"infomaniak","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null}},"name":"Infomaniak","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/io_net.js

@@ -1,5 +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};
+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":1351297,"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":29400,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":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":258748,"hf_likes":1043,"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":146538,"hf_likes":2458,"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":119357,"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":312172,"hf_likes":2952,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"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":107564,"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":44971,"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":51956,"hf_likes":1712,"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":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"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":7966494,"hf_likes":4923,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":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":27961,"hf_likes":1231,"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;