@agentjido/llmdb 2026.8.2

package/dist/providers/vivgrid.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "vivgrid",
+  "deepseek-v3.2" | "deepseek-v4-pro" | "gemini-3.1-flash-lite-preview" | "gemini-3.1-pro-preview" | "glm-5.2" | "gpt-5-mini" | "gpt-5.1-codex" | "gpt-5.1-codex-max" | "gpt-5.2-codex" | "gpt-5.3-codex" | "gpt-5.4" | "gpt-5.4-mini" | "gpt-5.4-nano" | "gpt-5.5" | "gpt-5.6-luna" | "gpt-5.6-sol" | "gpt-5.6-terra"
+>;
+export default provider;

package/dist/providers/vivgrid.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.vivgrid.com/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.vivgrid.com/models","env":["VIVGRID_API_KEY"],"exclude_models":null,"extra":null,"id":"vivgrid","models":{"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"deepseek-v3.2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.003625,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":1,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"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"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":false},"family":null,"id":"gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2026-01-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-01-14","retired":false,"tags":null},"gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-24","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Mini","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Nano","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"provider":{"npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Luna","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Sol","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":3.125,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Terra","pricing":null,"provider":"vivgrid","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null}},"name":"Vivgrid","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/vultr.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "vultr",
+  "MiniMaxAI/MiniMax-M2.7" | "Qwen/Qwen3.5-397B-A17B" | "Qwen/Qwen3.6-27B" | "XiaomiMiMo/MiMo-V2.5-Pro" | "deepseek-ai/DeepSeek-V4-Flash" | "moonshotai/Kimi-K2.6" | "nvidia/DeepSeek-V3.2-NVFP4" | "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16" | "nvidia/Nemotron-Cascade-2-30B-A3B" | "zai-org/GLM-5.2-FP8"
+>;
+export default provider;

package/dist/providers/vultr.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.vultrinference.com/v1","catalog_only":true,"config_schema":null,"doc":"https://api.vultrinference.com/","env":["VULTR_API_KEY"],"exclude_models":null,"extra":null,"id":"vultr","models":{"MiniMaxAI/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":917214,"hf_likes":1236,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"Qwen/Qwen3.5-397B-A17B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":416324,"hf_likes":1546,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.55,"output":1.65},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/MiMo-V2.5-Pro-GGUF"}],"hf_downloads":53020,"hf_likes":727,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","memory":{"min_ram_gb":571.8,"min_vram_gb":524.1,"recommended_ram_gb":953.0},"model_id":"XiaomiMiMo/MiMo-V2.5-Pro","moe":{"active_experts":8,"active_parameters":71413954340,"is_moe":true,"num_experts":384},"parameter_count":"1023.2B","parameters_raw":1023244718976,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5-Pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-04-24","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":0.3,"output":1.2},"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":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"nvidia/DeepSeek-V3.2-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":0.55,"output":1.65},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"nvidia/DeepSeek-V3.2-NVFP4","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","knowledge":"2025-05","last_updated":"2026-04-28","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Nano Omni","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"nvidia/Nemotron-Cascade-2-30B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":48235,"hf_likes":522,"matched_hugging_face_id":"nvidia/Nemotron-Cascade-2-30B-A3B","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/Nemotron-Cascade-2-30B-A3B","moe":{"active_experts":6,"active_parameters":2985101885,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577937344,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-03-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"nvidia/Nemotron-Cascade-2-30B-A3B","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron Cascade 2","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"zai-org/GLM-5.2-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":0.85,"output":3.1},"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":2780649,"hf_likes":244,"matched_hugging_face_id":"zai-org/GLM-5.2-FP8","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2-FP8","moe":{"active_experts":8,"active_parameters":60034633551,"is_moe":true,"num_experts":256},"parameter_count":"753.4B","parameters_raw":753375793584,"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":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2-FP8","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":393216,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"vultr","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Vultr","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/wafer_ai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "wafer_ai",
+  "GLM-5.1" | "GLM-5.2" | "Kimi-K2.6" | "MiniMax-M3" | "glm5.2-fast"
+>;
+export default provider;

package/dist/providers/wafer_ai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://pass.wafer.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.wafer.ai/wafer-pass","env":["WAFER_API_KEY"],"exclude_models":null,"extra":null,"id":"wafer_ai","models":{"GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":0,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General Language Model 5.1 — high-quality bilingual (EN/ZH) generation with strong coding and reasoning capabilities.","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"GLM-5.1","knowledge":"2025-04","last_updated":"2026-06-01","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"wafer_ai","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0,"input":1.2,"output":4.1},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"GLM-5.2","knowledge":null,"last_updated":"2026-06-22","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"wafer_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"cache_write":0,"input":1.14,"output":4.8},"deprecated":false,"extra":{"attachment":true,"description":"Kimi K2.6 sparse MoE model with a 262K context window. Available serverless and not included in standard Wafer Pass. Non-ZDR only: requests with `Wafer-ZDR: required` are rejected.","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":false},"family":null,"id":"Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"wafer_ai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"cache_write":0,"input":0.33,"output":1.32},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1048576,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"wafer_ai","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"glm5.2-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":0,"input":3,"output":10.25},"deprecated":false,"extra":{"attachment":false,"description":"The same model served for high TPS.","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm5.2-fast","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM5.2-Fast","pricing":null,"provider":"wafer_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Wafer","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/wandb.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "wandb",
+  "JetBrains/Mellum2-12B-A2.5B-Instruct" | "MiniMaxAI/MiniMax-M2.5" | "MiniMaxAI/MiniMax-M3" | "OpenPipe/Qwen3-14B-Instruct" | "Qwen/Qwen3-30B-A3B-Instruct-2507" | "Qwen/Qwen3-Coder-480B-A35B-Instruct" | "Qwen/Qwen3.5-35B-A3B" | "Qwen/Qwen3.6-27B" | "Qwen/Qwen3.6-35B-A3B" | "deepseek-ai/DeepSeek-V3.1" | "deepseek-ai/DeepSeek-V4-Flash" | "deepseek-ai/DeepSeek-V4-Flash-0731" | "deepseek-ai/DeepSeek-V4-Pro" | "google/gemma-4-31B-it" | "ibm-granite/granite-4.1-8b" | "meta-llama/Llama-3.1-70B-Instruct" | "meta-llama/Llama-3.1-8B-Instruct" | "meta-llama/Llama-3.3-70B-Instruct" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "moonshotai/Kimi-K3" | "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8" | "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2"
+>;
+export default provider;

package/dist/providers/wandb.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.inference.wandb.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.wandb.ai/guides/integrations/inference/","env":["WANDB_API_KEY"],"exclude_models":null,"extra":null,"id":"wandb","models":{"JetBrains/Mellum2-12B-A2.5B-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,"input":0.05,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"JetBrains/Mellum2-12B-A2.5B-Instruct","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mellum2 12B A2.5B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"MiniMaxAI/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","family":"minimax-m2.5","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":[],"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":"wandb","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"MiniMaxAI/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.23,"output":0.96},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax M3 is a multimodal MoE model with 23B active parameters optimized for coding and agentic workflows.","family":"minimax-m3","llmfit":{"architecture":"minimax_m3_vl","context_length":1048576,"discovered":false,"gguf_sources":[],"hf_downloads":164790,"hf_likes":1418,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M3","memory":{"min_ram_gb":238.6,"min_vram_gb":218.7,"recommended_ram_gb":397.7},"model_id":"MiniMaxAI/MiniMax-M3","moe":{"active_experts":4,"active_parameters":10000000000,"is_moe":true,"num_experts":128},"parameter_count":"427.0B","parameters_raw":427040140160,"pipeline_tag":"image-text-to-text","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-06-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M3","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax M3","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"OpenPipe/Qwen3-14B-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,"input":0.05,"output":0.22},"deprecated":false,"extra":{"attachment":false,"description":"An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":17462,"hf_likes":0,"matched_hugging_face_id":"OpenPipe/Qwen3-14B-Instruct","memory":{"min_ram_gb":8.3,"min_vram_gb":7.6,"recommended_ram_gb":13.8},"model_id":"OpenPipe/Qwen3-14B-Instruct","parameter_count":"14.8B","parameters_raw":14768307200,"pipeline_tag":"text-generation","provider":"openpipe","quantization":"Q4_K_M","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"OpenPipe/Qwen3-14B-Instruct","knowledge":null,"last_updated":"2025-04-29","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 14B Instruct","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"Qwen/Qwen3-30B-A3B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1902844,"hf_likes":822,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge":null,"last_updated":"2025-07-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-07-29","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"input":1,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Mixture-of-Experts model optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning.","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91304,"hf_likes":1357,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":"2025-04","last_updated":"2025-07-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"Qwen/Qwen3.5-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","family":"qwen3.5","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2582188,"hf_likes":1480,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":null,"last_updated":"2026-02-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-35B-A3B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"Qwen/Qwen3.6-27B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","family":"qwen3.6","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-27B","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","family":"qwen3.6","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-15","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":0.55,"output":1.65},"deprecated":false,"extra":{"attachment":false,"description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":273040,"hf_likes":825,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-21","lifecycle":null,"limits":{"context":161000,"output":161000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads.","family":"deepseek","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-24","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":0.07,"input":0.13,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4-Flash-0731 is an MoE model great for coding, reasoning, and agentic workloads.","family":"deepseek","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"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":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-ai/DeepSeek-V4-Pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.14,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning, coding, and complex agentic workloads.","family":"deepseek","llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.1,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","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":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"ibm-granite/granite-4.1-8b":{"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,"input":0.05,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","family":"granite","llmfit":{"architecture":"granite","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/granite-4.1-8b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/granite-4.1-8b-GGUF"}],"hf_downloads":4085575,"hf_likes":243,"matched_hugging_face_id":"ibm-granite/granite-4.1-8b","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"ibm-granite/granite-4.1-8b","parameter_count":"8.8B","parameters_raw":8791592960,"pipeline_tag":"text-generation","provider":"ibm-granite","quantization":"Q4_K_M","release_date":"2026-04-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"ibm-granite/granite-4.1-8b","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Granite 4.1 8B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"meta-llama/Llama-3.1-70B-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":0.8,"input":0.8,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[],"hf_downloads":812989,"hf_likes":938,"matched_hugging_face_id":"meta-llama/Llama-3.1-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.1-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-07-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.1-70B-Instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 70B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/Llama-3.1-8B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.22,"input":0.22,"output":0.22},"deprecated":false,"extra":{"attachment":false,"description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.1-8B-Instruct-GGUF"}],"hf_downloads":7886695,"hf_likes":6455,"matched_hugging_face_id":"meta-llama/Llama-3.1-8B-Instruct","memory":{"min_ram_gb":4.5,"min_vram_gb":4.1,"recommended_ram_gb":7.5},"model_id":"meta-llama/Llama-3.1-8B-Instruct","parameter_count":"8.0B","parameters_raw":8030261248,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-07-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.1-8B-Instruct","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2024-07-23","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":0.71,"input":0.71,"output":0.71},"deprecated":false,"extra":{"attachment":false,"description":"Multilingual model excelling in conversational tasks, detailed instruction-following, 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,"structured_output":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.65,"output":3.41},"deprecated":false,"extra":{"attachment":true,"description":"Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","family":"kimi-k2","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":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-04-20","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":0.15,"input":0.71,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Kimi K2.7 Code is a 1T-parameter MoE model with 32B active parameters purpose-built for long-horizon agentic coding and software engineering.","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"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":"wandb","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi K3 is a 2.8T-parameter multimodal MoE model with 104B active parameters built for long-horizon coding and agentic workflows.","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron 3 is a LatentMoE model designed to deliver strong agentic, reasoning, and conversational capabilities.","family":"nemotron","llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":210668,"hf_likes":271,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","memory":{"min_ram_gb":69.1,"min_vram_gb":63.3,"recommended_ram_gb":115.1},"model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","moe":{"active_experts":22,"active_parameters":11226390744,"is_moe":true,"num_experts":512},"parameter_count":"123.6B","parameters_raw":123611012096,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-03-10","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.75,"output":2.75},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.03,"output":0.17},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-120b","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":false,"description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","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,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-20b","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"zai-org/GLM-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":202752},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"wandb","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":0.14,"input":0.76,"output":2.42},"deprecated":false,"extra":{"attachment":false,"description":"GLM-5.2 is a Mixture-of-Experts language model featuring 40 billion activated parameters and a total of 744 billion parameters.","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"wandb","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null}},"name":"Weights & Biases","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/xai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "xai",
+  "grok-3" | "grok-3-mini" | "grok-3-mini-fast" | "grok-3-mini-fast-latest" | "grok-3-mini-latest" | "grok-4" | "grok-4-0709" | "grok-4-1-fast-non-reasoning" | "grok-4-1-fast-reasoning" | "grok-4-fast" | "grok-4-fast-non-reasoning" | "grok-4-fast-reasoning" | "grok-4.20" | "grok-4.20-0309" | "grok-4.20-0309-non-reasoning" | "grok-4.20-0309-reasoning" | "grok-4.20-beta" | "grok-4.20-beta-0309" | "grok-4.20-beta-0309-non-reasoning" | "grok-4.20-beta-0309-reasoning" | "grok-4.20-beta-latest" | "grok-4.20-beta-latest-non-reasoning" | "grok-4.20-beta-latest-reasoning" | "grok-4.20-beta-non-reasoning" | "grok-4.20-beta-reasoning" | "grok-4.20-experimental-beta-0304" | "grok-4.20-experimental-beta-0304-non-reasoning" | "grok-4.20-experimental-beta-0304-reasoning" | "grok-4.20-experimental-beta-latest" | "grok-4.20-experimental-beta-non-reasoning-latest" | "grok-4.20-experimental-beta-reasoning-latest" | "grok-4.20-multi-agent" | "grok-4.20-multi-agent-0309" | "grok-4.20-multi-agent-beta-0309" | "grok-4.20-multi-agent-beta-latest" | "grok-4.20-multi-agent-experimental-beta-0304" | "grok-4.20-multi-agent-experimental-beta-latest" | "grok-4.20-multi-agent-latest" | "grok-4.20-non-reasoning" | "grok-4.20-non-reasoning-gv2" | "grok-4.20-non-reasoning-latest" | "grok-4.20-reasoning" | "grok-4.20-reasoning-gv2" | "grok-4.20-reasoning-latest" | "grok-4.3" | "grok-4.3-latest" | "grok-4.5" | "grok-4.5-latest" | "grok-4.6" | "grok-build-0.1" | "grok-build-latest" | "grok-code-fast" | "grok-code-fast-1" | "grok-code-fast-1-0825" | "grok-imagine-image" | "grok-imagine-image-2.0" | "grok-imagine-image-2026-03-02" | "grok-imagine-image-pro" | "grok-imagine-image-quality" | "grok-imagine-image-quality-20260403" | "grok-imagine-image-quality-latest" | "grok-imagine-video" | "grok-imagine-video-1.5" | "grok-imagine-video-1.5-2026-05-30" | "grok-imagine-video-1.5-preview" | "grok-latest"
+>;
+export default provider;

package/dist/providers/xai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.x.ai/v1","config_schema":null,"doc":"https://docs.x.ai","env":["XAI_API_KEY"],"exclude_models":["grok-vision-beta","grok-beta","grok-2","grok-2-1212","grok-2-latest","grok-2-vision","grok-2-vision-1212","grok-2-vision-latest"],"extra":null,"id":"xai","models":{"grok-3":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-3","knowledge":null,"last_updated":null,"lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-3-mini","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-3-mini-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-3-mini-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-3-mini-fast-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-3-mini-fast-latest","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-3-mini-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-3-mini-latest","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-4","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-4-0709":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"cache_read":0.75,"input":3,"output":15,"reasoning":15},"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"open_weights":false,"temperature":true},"family":null,"id":"grok-4-0709","knowledge":"2025-07","last_updated":"2025-07-09","lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4","pricing":null,"provider":"xai","provider_model_id":"grok-4-0709","release_date":"2025-07-09","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":null,"lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":"grok-4-1-fast-non-reasoning","release_date":null,"retired":false,"tags":null},"grok-4-1-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.2,"output":0.5},"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"open_weights":false,"temperature":true},"family":null,"id":"grok-4-1-fast-reasoning","knowledge":"2025-07","last_updated":"2025-11-19","lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast Reasoning","pricing":null,"provider":"xai","provider_model_id":"grok-4-1-fast-reasoning","release_date":"2025-11-19","retired":false,"tags":null},"grok-4-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-4-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-4-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"cache_read":0.02,"input":0.2,"output":0.5},"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"open_weights":false,"temperature":true},"family":null,"id":"grok-4-fast-non-reasoning","knowledge":"2024-11","last_updated":"2025-09-21","lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":{"context":2000000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Grok 4 Fast Non-Reasoning","pricing":null,"provider":"xai","provider_model_id":"grok-4-fast-non-reasoning","release_date":"2025-09-21","retired":false,"tags":null},"grok-4-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"cache_read":0.02,"input":0.2,"output":0.5},"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"open_weights":false,"temperature":true},"family":null,"id":"grok-4-fast-reasoning","knowledge":"2024-11","last_updated":"2025-09-21","lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-4.3","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":{"context":2000000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Grok 4 Fast Reasoning","pricing":null,"provider":"xai","provider_model_id":"grok-4-fast-reasoning","release_date":"2025-09-21","retired":false,"tags":null},"grok-4.20-0309-non-reasoning":{"aliases":["grok-4.20-non-reasoning","grok-4.20-non-reasoning-latest","grok-4.20-beta-non-reasoning","grok-4.20-beta-latest-non-reasoning","grok-4.20-experimental-beta-0304-non-reasoning","grok-4.20-experimental-beta-non-reasoning-latest","grok-4.20-beta-0309-non-reasoning","grok-4.20-non-reasoning-gv2"],"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}},"cost":{"cache_read":0.2,"image":1.25,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"created":1773014400,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","structured_output":true,"temperature":true},"family":null,"id":"grok-4.20-0309-non-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":2.5,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.4,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":5.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"grok-4.20-0309-reasoning":{"aliases":["grok-4.20-reasoning-latest","grok-4.20","grok-4.20-reasoning","grok-4.20-0309","grok-4.20-beta-0309-reasoning","grok-4.20-beta","grok-4.20-beta-0309","grok-4.20-beta-latest","grok-4.20-beta-latest-reasoning","grok-4.20-beta-reasoning","grok-4.20-experimental-beta-0304-reasoning","grok-4.20-experimental-beta-0304","grok-4.20-experimental-beta-reasoning-latest","grok-4.20-experimental-beta-latest","grok-4.20-reasoning-gv2"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"image":1.25,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"created":1773014400,"description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.20-0309-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":2.5,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.4,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":5.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"grok-4.20-multi-agent-0309":{"aliases":["grok-4.20-multi-agent","grok-4.20-multi-agent-latest","grok-4.20-multi-agent-beta-latest","grok-4.20-multi-agent-experimental-beta-0304","grok-4.20-multi-agent-experimental-beta-latest","grok-4.20-multi-agent-beta-0309"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"cache_read":0.2,"image":1.25,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"created":1773014400,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.20-multi-agent-0309","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Multi-Agent","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":2.5,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.4,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":5.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"grok-4.3":{"aliases":["grok-4.3-latest","grok-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"image":1.25,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"constraints":{"reasoning_effort":"supported","reasoning_effort_values":["low","medium","high"]},"created":1776384000,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.3","knowledge":null,"last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":2.5,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.4,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":5.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":"grok-4.3","release_date":"2026-05-07","retired":false,"tags":null},"grok-4.5":{"aliases":["grok-4.5-latest","grok-build-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"image":2.0,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"created":1782691200,"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":4.0,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.6,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":12.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"grok-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"schema":true},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"image":2.0,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"constraints":{"reasoning_effort":"required","reasoning_effort_values":["low","medium","high","xhigh"]},"created":1785974400,"long_context_threshold":200000,"owned_by":"xai"},"family":null,"id":"grok-4.6","knowledge":"2026-02-01","last_updated":"2026-08-12","lifecycle":null,"limits":{"context":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.6","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":4.0,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":1.0,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":12.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":"grok-4.6","release_date":"2026-08-12","retired":false,"tags":null},"grok-build-0.1":{"aliases":["grok-code-fast-1","grok-code-fast","grok-code-fast-1-0825"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"image":1.0,"input":1.0,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"created":1776297600,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","long_context_threshold":200000,"open_weights":false,"owned_by":"xai","reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":{"components":[{"id":"token.input.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":2.0,"unit":"token"},{"id":"token.cache_read.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":0.4,"unit":"token"},{"id":"token.output.long_context","kind":"token","notes":"Applies above 200000 context tokens","per":1000000,"rate":4.0,"unit":"token"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"grok-code-fast-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":null,"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-code-fast-1","knowledge":null,"last_updated":null,"lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-build-0.1","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-imagine-image":{"aliases":["grok-imagine-image-2026-03-02"],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false}},"cost":null,"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"api":"images","attachment":true,"created":1769558400,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"owned_by":"xai","temperature":false},"family":"grok-imagine","id":"grok-imagine-image","knowledge":null,"last_updated":"2026-01-28","lifecycle":null,"limits":{"context":8000},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"model":null,"name":"Grok Imagine Image","pricing":{"components":[{"id":"image.input","kind":"image","per":1,"rate":0.002,"unit":"image"},{"id":"image.generated","kind":"image","per":1,"rate":0.02,"unit":"image"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"grok-imagine-image-2.0":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"created":1786147200,"owned_by":"xai"},"family":null,"id":"grok-imagine-image-2.0","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8000},"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-imagine-image-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":true,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":null,"family":null,"id":"grok-imagine-image-pro","knowledge":null,"last_updated":null,"lifecycle":{"deprecated_at":"2026-05-07","replacement":"grok-imagine-image-quality","retires_at":"2026-05-15T19:00:00Z","status":"deprecated"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"xai","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"grok-imagine-image-quality":{"aliases":["grok-imagine-image-quality-20260403","grok-imagine-image-quality-latest","grok-imagine-image-pro"],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"created":1775174400,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"owned_by":"xai","temperature":false},"family":null,"id":"grok-imagine-image-quality","knowledge":null,"last_updated":"2026-04-03","lifecycle":null,"limits":{"context":8000},"modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"model":null,"name":"Grok Imagine Image Quality","pricing":{"components":[{"id":"image.input","kind":"image","per":1,"rate":0.01,"unit":"image"},{"id":"image.output.1k","kind":"image","per":1,"rate":0.05,"size_class":"1K","unit":"image"},{"id":"image.output.2k","kind":"image","per":1,"rate":0.07,"size_class":"2K","unit":"image"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"grok-imagine-video":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"created":1769558400,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"owned_by":"xai","temperature":false},"family":null,"id":"grok-imagine-video","knowledge":null,"last_updated":"2026-01-28","lifecycle":null,"limits":{"context":1024},"modalities":{"input":["text","image","video","pdf"],"output":["video"]},"model":null,"name":"Grok Imagine Video","pricing":{"components":[{"id":"image.input","kind":"image","per":1,"rate":0.002,"unit":"image"},{"id":"video.input.second","kind":"other","meter":"input_video_second","per":1,"rate":0.01,"unit":"other"},{"id":"video.output.480p.second","kind":"other","meter":"video_second","per":1,"rate":0.05,"size_class":"480p","unit":"other"},{"id":"video.output.720p.second","kind":"other","meter":"video_second","per":1,"rate":0.07,"size_class":"720p","unit":"other"}],"currency":"USD","merge":"merge_by_id"},"provider":"xai","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"grok-imagine-video-1.5":{"aliases":["grok-imagine-video-1.5-preview","grok-imagine-video-1.5-2026-05-30"],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"created":1779840000,"description":"Video model for image-to-video generation, editing, and extension workflows","family":"grok","open_weights":false,"owned_by":"xai","temperature":false},"family":null,"id":"grok-imagine-video-1.5","knowledge":null,"last_updated":"2026-05-30","lifecycle":null,"limits":{"context":1024},"modalities":{"input":["text","image","audio","pdf"],"output":["video"]},"model":null,"name":"Grok Imagine Video 1.5","pricing":null,"provider":"xai","provider_model_id":null,"release_date":"2026-05-30","retired":false,"tags":null}},"name":"xAI","pricing_defaults":{"components":[{"id":"tool.web_search","kind":"tool","per":1000,"rate":5.0,"tool":"web_search","unit":"call"},{"id":"tool.x_search","kind":"tool","per":1000,"rate":5.0,"tool":"x_search","unit":"call"},{"id":"tool.code_execution","kind":"tool","per":1000,"rate":5.0,"tool":"code_execution","unit":"call"},{"id":"tool.code_interpreter","kind":"tool","per":1000,"rate":5.0,"tool":"code_interpreter","unit":"call"},{"id":"tool.attachment_search","kind":"tool","per":1000,"rate":10.0,"tool":"attachment_search","unit":"call"},{"id":"tool.collections_search","kind":"tool","per":1000,"rate":2.5,"tool":"collections_search","unit":"call"},{"id":"tool.file_search","kind":"tool","per":1000,"rate":2.5,"tool":"file_search","unit":"call"}],"currency":"USD"},"runtime":{"auth":{"env":["XAI_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.x.ai/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://docs.x.ai"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/xiaomi.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "xiaomi",
+  "mimo-v2-flash" | "mimo-v2-omni" | "mimo-v2-pro" | "mimo-v2.5" | "mimo-v2.5-pro" | "mimo-v2.5-pro-ultraspeed"
+>;
+export default provider;

package/dist/providers/xiaomi.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.xiaomimimo.com/v1","catalog_only":true,"config_schema":null,"doc":"https://platform.xiaomimimo.com/#/docs","env":["XIAOMI_API_KEY"],"exclude_models":null,"extra":null,"id":"xiaomi","models":{"mimo-v2-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Legacy model retained for compatibility with older integrations","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","temperature":true},"family":null,"id":"mimo-v2-flash","knowledge":"2024-12-01","last_updated":"2026-06-24","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Flash","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"mimo-v2-omni":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","temperature":true},"family":null,"id":"mimo-v2-omni","knowledge":"2024-12","last_updated":"2026-06-24","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"MiMo-V2-Omni","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"mimo-v2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0036,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"toggle"}],"status":"deprecated","temperature":true},"family":null,"id":"mimo-v2-pro","knowledge":"2024-12","last_updated":"2026-06-24","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Pro","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"mimo-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"mimo-v2.5","knowledge":"2024-12","last_updated":"2026-06-24","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"mimo-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0036,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-06-24","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"mimo-v2.5-pro-ultraspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.0108,"input":1.305,"output":2.61},"deprecated":false,"extra":{"attachment":false,"description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"status":"beta","temperature":true},"family":null,"id":"mimo-v2.5-pro-ultraspeed","knowledge":"2024-12","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro-UltraSpeed","pricing":null,"provider":"xiaomi","provider_model_id":null,"release_date":"2026-06-08","retired":false,"tags":null}},"name":"Xiaomi","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/xiaomi_token_plan_ams.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "xiaomi_token_plan_ams",
+  "mimo-v2-pro" | "mimo-v2-tts" | "mimo-v2.5" | "mimo-v2.5-pro" | "mimo-v2.5-tts" | "mimo-v2.5-tts-voiceclone" | "mimo-v2.5-tts-voicedesign"
+>;
+export default provider;