@agentjido/llmdb 2026.8.2

package/dist/providers/llmtr.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "llmtr",
+  "gemma-4" | "magibu-11b-v8" | "medgemma-4b" | "qwen3-6-35b" | "sincap" | "trendyol-7b"
+>;
+export default provider;

package/dist/providers/llmtr.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://llmtr.com/v1","catalog_only":true,"config_schema":null,"doc":"https://llmtr.com/docs","env":["LLMTR_API_KEY"],"exclude_models":null,"extra":null,"id":"llmtr","models":{"gemma-4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","open_weights":true,"temperature":true},"family":null,"id":"gemma-4","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"magibu-11b-v8":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","open_weights":false,"temperature":true},"family":null,"id":"magibu-11b-v8","knowledge":null,"last_updated":"2026-06-05","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magibu 11B v8","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-06-05","retired":false,"tags":null},"medgemma-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":true,"temperature":true},"family":null,"id":"medgemma-4b","knowledge":null,"last_updated":"2026-04-26","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MedGemma 4B","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-04-26","retired":false,"tags":null},"qwen3-6-35b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-35b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":16384,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"sincap":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","open_weights":false,"temperature":true},"family":null,"id":"sincap","knowledge":null,"last_updated":"2026-05-05","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sincap","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"trendyol-7b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"trendyol-7b","knowledge":null,"last_updated":"2026-06-06","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trendyol 7B","pricing":null,"provider":"llmtr","provider_model_id":null,"release_date":"2026-06-06","retired":false,"tags":null}},"name":"LLMTR","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/lmstudio.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "lmstudio",
+  "openai/gpt-oss-20b" | "qwen/qwen3-30b-a3b-2507" | "qwen/qwen3-coder-30b"
+>;
+export default provider;

package/dist/providers/lmstudio.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"http://127.0.0.1:1234/v1","catalog_only":true,"config_schema":null,"doc":"https://lmstudio.ai/models","env":["LMSTUDIO_API_KEY"],"exclude_models":null,"extra":null,"id":"lmstudio","models":{"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":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"lmstudio","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwen3-30b-a3b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-2507","knowledge":"2025-04","last_updated":"2025-07-30","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B 2507","pricing":null,"provider":"lmstudio","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"qwen/qwen3-coder-30b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-30b","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30B","pricing":null,"provider":"lmstudio","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null}},"name":"LMStudio","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/longcat.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "longcat",
+  "LongCat-2.0"
+>;
+export default provider;

package/dist/providers/longcat.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.longcat.chat/openai","catalog_only":true,"config_schema":null,"doc":"https://longcat.chat/platform/docs/","env":["LONGCAT_API_KEY"],"exclude_models":null,"extra":null,"id":"longcat","models":{"LongCat-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.015,"input":0.75,"output":2.95},"deprecated":false,"extra":{"attachment":false,"description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"LongCat-2.0","knowledge":null,"last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"LongCat-2.0","pricing":null,"provider":"longcat","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null}},"name":"LongCat","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/lucidquery.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "lucidquery",
+  "lucidnova-rf1-100b" | "lucidquery-agi-01-frontier" | "lucidquery-agi-01-swift" | "lucidquery-nexus-coder"
+>;
+export default provider;

package/dist/providers/lucidquery.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.lucidquery.com/v1","catalog_only":true,"config_schema":null,"doc":"https://lucidquery.com/docs","env":["LUCIDQUERY_API_KEY"],"exclude_models":null,"extra":null,"id":"lucidquery","models":{"lucidnova-rf1-100b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nova","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"lucidnova-rf1-100b","knowledge":"2025-09-16","last_updated":"2025-09-10","lifecycle":null,"limits":{"context":120000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"LucidNova RF1 100B","pricing":null,"provider":"lucidquery","provider_model_id":null,"release_date":"2024-12-28","retired":false,"tags":null},"lucidquery-agi-01-frontier":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":4.5,"output":22},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"lucidquery-agi-01-frontier","knowledge":"2026-06-05","last_updated":"2026-06-16","lifecycle":null,"limits":{"context":300000,"output":120000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"AGI-01 Frontier","pricing":null,"provider":"lucidquery","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null},"lucidquery-agi-01-swift":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"lucidquery-agi-01-swift","knowledge":"2026-06-05","last_updated":"2026-06-16","lifecycle":null,"limits":{"context":300000,"output":120000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"AGI-01 Swift","pricing":null,"provider":"lucidquery","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null},"lucidquery-nexus-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"lucid","open_weights":false,"reasoning_options":[],"temperature":false},"family":null,"id":"lucidquery-nexus-coder","knowledge":"2025-08-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":250000,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"LucidQuery Nexus Coder","pricing":null,"provider":"lucidquery","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null}},"name":"LucidQuery","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/lynkr.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "lynkr",
+  "lynkr-auto"
+>;
+export default provider;

package/dist/providers/lynkr.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"http://127.0.0.1:8081/v1","catalog_only":true,"config_schema":null,"doc":"https://github.com/Fast-Editor/Lynkr","env":["LYNKR_API_KEY"],"exclude_models":null,"extra":null,"id":"lynkr","models":{"lynkr-auto":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Virtual model: Lynkr scores each request on complexity and routes it to the tier model the user configured (local Ollama/llama.cpp for simple requests, configured cloud providers for complex ones).","family":"auto","open_weights":false,"temperature":true},"family":null,"id":"lynkr-auto","knowledge":null,"last_updated":"2026-07-11","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Lynkr Auto (complexity routing)","pricing":null,"provider":"lynkr","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null}},"name":"Lynkr","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/meganova.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "meganova",
+  "MiniMaxAI/MiniMax-M2.1" | "MiniMaxAI/MiniMax-M2.5" | "Qwen/Qwen2.5-VL-32B-Instruct" | "Qwen/Qwen3-235B-A22B-Instruct-2507" | "Qwen/Qwen3.5-Plus" | "XiaomiMiMo/MiMo-V2-Flash" | "deepseek-ai/DeepSeek-R1-0528" | "deepseek-ai/DeepSeek-V3-0324" | "deepseek-ai/DeepSeek-V3.1" | "deepseek-ai/DeepSeek-V3.2" | "deepseek-ai/DeepSeek-V3.2-Exp" | "meta-llama/Llama-3.3-70B-Instruct" | "mistralai/Mistral-Nemo-Instruct-2407" | "mistralai/Mistral-Small-3.2-24B-Instruct-2506" | "moonshotai/Kimi-K2-Thinking" | "moonshotai/Kimi-K2.5" | "zai-org/GLM-4.6" | "zai-org/GLM-4.7" | "zai-org/GLM-5"
+>;
+export default provider;

package/dist/providers/meganova.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.meganova.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.meganova.ai","env":["MEGANOVA_API_KEY"],"exclude_models":null,"extra":null,"id":"meganova","models":{"MiniMaxAI/MiniMax-M2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.1-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.1-GGUF"}],"hf_downloads":12798,"hf_likes":0,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.1","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.1","moe":{"active_experts":8,"active_parameters":18223715635,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228689764864,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.1","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-12-23","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":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"Qwen/Qwen2.5-VL-32B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-VL-32B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen2.5-VL-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-VL-32B-Instruct-GGUF"}],"hf_downloads":1072669,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen2.5-VL-32B-Instruct","memory":{"min_ram_gb":18.7,"min_vram_gb":17.1,"recommended_ram_gb":31.2},"model_id":"Qwen/Qwen2.5-VL-32B-Instruct","parameter_count":"33.5B","parameters_raw":33452718336,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen2.5-VL-32B-Instruct","knowledge":null,"last_updated":"2025-03-24","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5 VL 32B Instruct","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-03-24","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF"}],"hf_downloads":59827,"hf_likes":793,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-21","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge":null,"last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"Qwen/Qwen3.5-Plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3.5-Plus","knowledge":"2025-04","last_updated":"2026-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 Plus","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2026-02","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","llmfit":{"architecture":"mimo_v2_flash","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiMo-V2-Flash-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiMo-V2-Flash-GGUF"}],"hf_downloads":90789,"hf_likes":747,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2-Flash","memory":{"min_ram_gb":173.1,"min_vram_gb":158.7,"recommended_ram_gb":288.5},"model_id":"XiaomiMiMo/MiMo-V2-Flash","moe":{"active_experts":8,"active_parameters":15000000000,"is_moe":true,"num_experts":256},"parameter_count":"309.8B","parameters_raw":309785318400,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2025-12-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2-Flash","knowledge":"2024-12-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":262144,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo V2 Flash","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":2.15},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":206900,"hf_likes":2457,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1-0528","knowledge":"2024-07","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 0528","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.88},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":899240,"hf_likes":3151,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3-0324","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":"2025-03-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3-0324","knowledge":null,"last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-03-24","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":{"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":273040,"hf_likes":825,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.1","knowledge":null,"last_updated":"2025-08-25","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-08-25","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.26,"output":0.38},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1238427,"hf_likes":1462,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":null,"last_updated":"2025-12-03","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"deepseek-ai/DeepSeek-V3.2-Exp":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":252109,"hf_likes":993,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2-Exp","moe":{"active_experts":8,"active_parameters":54617567164,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2-Exp","knowledge":null,"last_updated":"2025-10-10","lifecycle":null,"limits":{"context":164000,"output":164000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2 Exp","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-10-10","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":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":478538,"hf_likes":2936,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"meta-llama/Llama-3.3-70B-Instruct","knowledge":null,"last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"mistralai/Mistral-Nemo-Instruct-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.04},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Nemo-Instruct-2407","knowledge":null,"last_updated":"2024-07-18","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Nemo Instruct 2407","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","knowledge":"2024-10","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"moonshotai/Kimi-K2-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.6},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":62805,"hf_likes":1714,"matched_hugging_face_id":"moonshotai/Kimi-K2-Thinking","memory":{"min_ram_gb":591.3,"min_vram_gb":542.0,"recommended_ram_gb":985.4},"model_id":"moonshotai/Kimi-K2-Thinking","moe":{"active_experts":8,"active_parameters":73847838596,"is_moe":true,"num_experts":384},"parameter_count":"1058.1B","parameters_raw":1058118284416,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-11-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2-Thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":2.8},"deprecated":false,"extra":{"attachment":false,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2026-01","last_updated":"2026-01-27","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"zai-org/GLM-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.45,"output":1.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai-org/GLM-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.8,"output":2.56},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai-org/GLM-5","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"meganova","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null}},"name":"Meganova","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/merge_gateway.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "merge_gateway",
+  "anthropic/claude-3-7-sonnet-20250219" | "anthropic/claude-fable-5" | "anthropic/claude-haiku-4-5-20251001" | "anthropic/claude-opus-4-1-20250805" | "anthropic/claude-opus-4-20250514" | "anthropic/claude-opus-4-5-20251101" | "anthropic/claude-opus-4-6" | "anthropic/claude-opus-4-7" | "anthropic/claude-opus-4-8" | "anthropic/claude-opus-5" | "anthropic/claude-sonnet-4-20250514" | "anthropic/claude-sonnet-4-5-20250929" | "anthropic/claude-sonnet-4-6" | "anthropic/claude-sonnet-5" | "bytedance/dola-seed-2.0-code" | "bytedance/dola-seed-2.0-code-preview" | "bytedance/dola-seed-2.0-lite" | "bytedance/dola-seed-2.0-mini" | "bytedance/dola-seed-2.0-pro" | "cohere/command-a-03-2025" | "cohere/command-r-08-2024" | "cohere/command-r-plus-08-2024" | "cohere/command-r7b-12-2024" | "deepseek/deepseek-r1" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-pro" | "google/gemini-2.5-computer-use-preview-10-2025" | "google/gemini-2.5-flash" | "google/gemini-2.5-flash-lite" | "google/gemini-2.5-pro" | "google/gemini-3-flash-preview" | "google/gemini-3-pro-preview" | "google/gemini-3.1-flash-lite" | "google/gemini-3.1-flash-lite-preview" | "google/gemini-3.1-pro-preview" | "google/gemini-3.1-pro-preview-customtools" | "google/gemini-3.5-flash" | "google/gemini-3.5-flash-lite" | "google/gemini-3.6-flash" | "google/gemini-embedding-001" | "google/gemini-flash-latest" | "google/gemini-flash-lite-latest" | "google/gemma-4-26b-a4b-it" | "google/gemma-4-31b-it" | "meta/llama-3.3-70b-instruct" | "meta/muse-spark-1.1" | "minimax/minimax-m2" | "minimax/minimax-m2.1" | "minimax/minimax-m2.5" | "minimax/minimax-m2.5-highspeed" | "minimax/minimax-m2.7" | "minimax/minimax-m2.7-highspeed" | "minimax/minimax-m3" | "mistral/codestral-latest" | "mistral/devstral-2512" | "mistral/devstral-medium-2507" | "mistral/devstral-medium-latest" | "mistral/devstral-small-2507" | "mistral/magistral-medium-latest" | "mistral/mistral-large-2411" | "mistral/mistral-large-2512" | "mistral/mistral-large-latest" | "mistral/mistral-medium-2505" | "mistral/mistral-medium-latest" | "mistral/mistral-small-latest" | "mistral/pixtral-large-latest" | "moonshot/kimi-k2.5" | "moonshot/kimi-k2.6" | "moonshot/kimi-k2.7-code" | "moonshot/kimi-k2.7-code-highspeed" | "moonshot/kimi-k3" | "moonshotai/kimi-k2-thinking" | "nvidia/nemotron-nano-9b-v2" | "openai/gpt-3.5-turbo" | "openai/gpt-4" | "openai/gpt-4-turbo" | "openai/gpt-4.1" | "openai/gpt-4.1-mini" | "openai/gpt-4.1-nano" | "openai/gpt-4o" | "openai/gpt-4o-2024-05-13" | "openai/gpt-4o-2024-08-06" | "openai/gpt-4o-2024-11-20" | "openai/gpt-4o-mini" | "openai/gpt-5" | "openai/gpt-5-chat-latest" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5.1" | "openai/gpt-5.1-chat-latest" | "openai/gpt-5.2" | "openai/gpt-5.2-chat-latest" | "openai/gpt-5.3-chat-latest" | "openai/gpt-5.4" | "openai/gpt-5.4-mini" | "openai/gpt-5.4-nano" | "openai/gpt-5.5" | "openai/gpt-5.6-luna" | "openai/gpt-5.6-sol" | "openai/gpt-5.6-terra" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "openai/gpt-oss-safeguard-120b" | "openai/o1" | "openai/o3" | "openai/o3-mini" | "openai/o4-mini" | "qwen/qwen-flash" | "qwen/qwen-plus" | "qwen/qwen3-235b-a22b" | "qwen/qwen3-32b" | "qwen/qwen3-coder-480b-a35b-instruct" | "qwen/qwen3-coder-flash" | "qwen/qwen3-coder-plus" | "qwen/qwen3-max" | "qwen/qwen3-next-80b-a3b-instruct" | "qwen/qwen3-next-80b-a3b-thinking" | "qwen/qwen3-vl-plus" | "qwen/qwen3.5-122b-a10b" | "qwen/qwen3.5-27b" | "qwen/qwen3.5-35b-a3b" | "qwen/qwen3.5-397b-a17b" | "qwen/qwen3.5-9b" | "qwen/qwen3.5-plus" | "qwen/qwen3.6-27b" | "qwen/qwen3.6-35b-a3b" | "qwen/qwen3.6-flash" | "qwen/qwen3.6-max-preview" | "qwen/qwen3.6-plus" | "qwen/qwen3.7-max" | "qwen/qwen3.7-plus" | "qwen/qwen3.8-max" | "sakana/fugu-ultra" | "thinkingmachines/inkling" | "writer/palmyra-x4" | "writer/palmyra-x5" | "xai/grok-4.20-0309-non-reasoning" | "xai/grok-4.20-0309-reasoning" | "xai/grok-4.3" | "xai/grok-4.5" | "xai/grok-build-0.1" | "zai/glm-4.5" | "zai/glm-4.5-air" | "zai/glm-4.5v" | "zai/glm-4.6" | "zai/glm-4.7" | "zai/glm-4.7-flash" | "zai/glm-4.7-flashx" | "zai/glm-5" | "zai/glm-5-turbo" | "zai/glm-5.1" | "zai/glm-5.2"
+>;
+export default provider;