@agentjido/llmdb 2026.8.2

package/dist/providers/hpc_ai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "hpc_ai",
+  "anthropic/claude-opus-4.7" | "deepseek/deepseek-v4-flash" | "deepseek/deepseek-v4-pro" | "minimax/minimax-m2.5" | "moonshotai/kimi-k2.5" | "moonshotai/kimi-k2.7-code" | "openai/gpt-5.5" | "zai-org/glm-5.1" | "zai-org/glm-5.2"
+>;
+export default provider;

package/dist/providers/hpc_ai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.hpc-ai.com/inference/v1","catalog_only":true,"config_schema":null,"doc":"https://www.hpc-ai.com/doc/docs/quickstart/","env":["HPC_AI_API_KEY"],"exclude_models":null,"extra":null,"id":"hpc_ai","models":{"anthropic/claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"deepseek/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":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.145,"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1002000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"minimax/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":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":196000,"output":195000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"moonshotai/kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-01","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":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","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":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"openai/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,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-04-23","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":0.133,"input":0.615,"output":2.46},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-5.1","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":202000,"output":202000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"zai-org/glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"hpc_ai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"HPC-AI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/huggingface.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "huggingface",
+  "MiniMaxAI/MiniMax-M2" | "MiniMaxAI/MiniMax-M2.1" | "MiniMaxAI/MiniMax-M2.5" | "MiniMaxAI/MiniMax-M2.7" | "MiniMaxAI/MiniMax-M3" | "Qwen/Qwen3-235B-A22B" | "Qwen/Qwen3-235B-A22B-Thinking-2507" | "Qwen/Qwen3-32B" | "Qwen/Qwen3-Coder-30B-A3B-Instruct" | "Qwen/Qwen3-Coder-480B-A35B-Instruct" | "Qwen/Qwen3-Coder-Next" | "Qwen/Qwen3-Embedding-4B" | "Qwen/Qwen3-Embedding-8B" | "Qwen/Qwen3-Next-80B-A3B-Instruct" | "Qwen/Qwen3-Next-80B-A3B-Thinking" | "Qwen/Qwen3.5-122B-A10B" | "Qwen/Qwen3.5-27B" | "Qwen/Qwen3.5-35B-A3B" | "Qwen/Qwen3.5-397B-A17B" | "Qwen/Qwen3.5-9B" | "Qwen/Qwen3.6-27B" | "Qwen/Qwen3.6-35B-A3B" | "XiaomiMiMo/MiMo-V2-Flash" | "XiaomiMiMo/MiMo-V2.5" | "XiaomiMiMo/MiMo-V2.5-Pro" | "deepseek-ai/DeepSeek-R1" | "deepseek-ai/DeepSeek-R1-0528" | "deepseek-ai/DeepSeek-V3.2" | "deepseek-ai/DeepSeek-V4-Flash" | "deepseek-ai/DeepSeek-V4-Flash-0731" | "deepseek-ai/DeepSeek-V4-Pro" | "google/gemma-4-26B-A4B-it" | "google/gemma-4-31B-it" | "meta-llama/Llama-3.3-70B-Instruct" | "moonshotai/Kimi-K2-Instruct" | "moonshotai/Kimi-K2-Instruct-0905" | "moonshotai/Kimi-K2-Thinking" | "moonshotai/Kimi-K2.5" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "moonshotai/Kimi-K3" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "stepfun-ai/Step-3.5-Flash" | "stepfun-ai/Step-3.7-Flash" | "tencent/Hy3" | "thinkingmachines/Inkling" | "thinkingmachines/Inkling-Small" | "zai-org/GLM-4.5" | "zai-org/GLM-4.5-Air" | "zai-org/GLM-4.5V" | "zai-org/GLM-4.6" | "zai-org/GLM-4.7" | "zai-org/GLM-4.7-Flash" | "zai-org/GLM-5" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2"
+>;
+export default provider;

package/dist/providers/huggingface.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://router.huggingface.co/v1","catalog_only":true,"config_schema":null,"doc":"https://huggingface.co/docs/inference-providers","env":["HF_TOKEN"],"exclude_models":null,"extra":null,"id":"huggingface","models":{"MiniMaxAI/MiniMax-M2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2-GGUF"}],"hf_downloads":108116,"hf_likes":1500,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2","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","release_date":"2025-10-22","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"MiniMaxAI/MiniMax-M2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"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":0.3,"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-M2.1-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":"2025-10","last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.1","pricing":null,"provider":"huggingface","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":{"cache_read":0.03,"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":"huggingface","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"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":{"cache_read":0.06,"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":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":[],"structured_output":true,"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":"huggingface","provider_model_id":null,"release_date":"2026-03-18","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":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","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":"2026-06-01","lifecycle":null,"limits":{"context":524288,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-235B-A22B-GGUF"}],"hf_downloads":702999,"hf_likes":1105,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B","moe":{"active_experts":8,"active_parameters":22000000000,"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":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B-A22B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-235B-A22B-Thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF"}],"hf_downloads":29970,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","knowledge":"2025-04","last_updated":"2025-07-25","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B-Thinking-2507","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"Qwen/Qwen3-32B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.29,"output":0.59},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-32B","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Coder-30B-A3B-Instruct-GGUF"}],"hf_downloads":1462772,"hf_likes":1187,"matched_hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","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":"2025-07-31","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"Qwen/Qwen3-Coder-480B-A35B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code 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,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":66536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-480B-A35B-Instruct","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"Qwen/Qwen3-Coder-Next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-Next-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Coder-Next-GGUF"}],"hf_downloads":552224,"hf_likes":1568,"matched_hugging_face_id":"Qwen/Qwen3-Coder-Next","memory":{"min_ram_gb":44.5,"min_vram_gb":40.8,"recommended_ram_gb":74.2},"model_id":"Qwen/Qwen3-Coder-Next","moe":{"active_experts":10,"active_parameters":3000000000,"is_moe":true,"num_experts":512},"parameter_count":"79.7B","parameters_raw":79674391296,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-01-30","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Coder-Next","knowledge":"2025-04","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-Next","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"Qwen/Qwen3-Embedding-4B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3-Embedding-4B-GGUF"}],"hf_downloads":3288621,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-4B","memory":{"min_ram_gb":2.2,"min_vram_gb":2.1,"recommended_ram_gb":3.7},"model_id":"Qwen/Qwen3-Embedding-4B","parameter_count":"4.0B","parameters_raw":4021774336,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"open_weights":true,"temperature":false},"family":null,"id":"Qwen/Qwen3-Embedding-4B","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":32000,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Embedding 4B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"Qwen/Qwen3-Embedding-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":3352596,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-8B","memory":{"min_ram_gb":4.2,"min_vram_gb":3.9,"recommended_ram_gb":7.0},"model_id":"Qwen/Qwen3-Embedding-8B","parameter_count":"7.6B","parameters_raw":7567295488,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"open_weights":true,"temperature":false},"family":null,"id":"Qwen/Qwen3-Embedding-8B","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Embedding 8B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Instruct-GGUF"}],"hf_downloads":285987,"hf_likes":1042,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","knowledge":"2025-04","last_updated":"2025-09-11","lifecycle":null,"limits":{"context":262144,"output":66536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Instruct","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"Qwen/Qwen3-Next-80B-A3B-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF"}],"hf_downloads":37095,"hf_likes":492,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"temperature":true},"family":null,"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","knowledge":"2025-04","last_updated":"2025-09-11","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next-80B-A3B-Thinking","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"Qwen/Qwen3.5-122B-A10B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2114418,"hf_likes":603,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"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":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-122B-A10B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"Qwen/Qwen3.5-27B":{"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":2.4},"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/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2666483,"hf_likes":1023,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"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":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-27B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-23","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":{"input":0.25,"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_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":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-35B-A3B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-23","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":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","interleaved":{"field":"reasoning_content"},"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":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"Qwen/Qwen3.5-397B-A17B","knowledge":"2025-04","last_updated":"2026-02-01","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5-397B-A17B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"Qwen/Qwen3.5-9B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.17,"output":0.25},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":12236962,"hf_likes":1781,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.5-9B","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-02-23","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":0.47,"output":3.19},"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"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"huggingface","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":{"input":0.15,"output":0.95},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":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":[],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-04-17","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","last_updated":"2025-12-16","lifecycle":null,"limits":{"context":262144,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2-Flash","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"XiaomiMiMo/MiMo-V2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"MiMo model for long-context reasoning, perception, and agentic tasks","family":"mimo","llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":359231,"hf_likes":383,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5","memory":{"min_ram_gb":173.7,"min_vram_gb":159.2,"recommended_ram_gb":289.4},"model_id":"XiaomiMiMo/MiMo-V2.5","moe":{"active_experts":8,"active_parameters":24764886000,"is_moe":true,"num_experts":256},"parameter_count":"310.8B","parameters_raw":310775040000,"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"XiaomiMiMo/MiMo-V2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"huggingface","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":1,"output":3},"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"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":"huggingface","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.7,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":9604023,"hf_likes":13537,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"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":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":64000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-ai/DeepSeek-R1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":206900,"hf_likes":2457,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-R1-0528","knowledge":"2025-05","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1-0528","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-05-28","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":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.28,"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":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,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V3.2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-12-01","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":0.14,"output":0.28},"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":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"huggingface","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":{"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"huggingface","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":0.003625,"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"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["high"]}],"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":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.59,"output":0.79},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","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":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"moonshotai/Kimi-K2-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","llmfit":{"architecture":"kimi_k2","context_length":4194304,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2-Instruct-GGUF"}],"hf_downloads":177689,"hf_likes":2371,"matched_hugging_face_id":"moonshotai/Kimi-K2-Instruct","memory":{"min_ram_gb":573.6,"min_vram_gb":525.8,"recommended_ram_gb":956.0},"model_id":"moonshotai/Kimi-K2-Instruct","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1026.5B","parameters_raw":1026470731056,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-07-11","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2-Instruct","knowledge":"2024-10","last_updated":"2025-07-14","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi-K2-Instruct","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-07-14","retired":false,"tags":null},"moonshotai/Kimi-K2-Instruct-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":66851,"hf_likes":787,"matched_hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","memory":{"min_ram_gb":573.6,"min_vram_gb":525.8,"recommended_ram_gb":956.0},"model_id":"moonshotai/Kimi-K2-Instruct-0905","moe":{"active_experts":8,"active_parameters":71639103404,"is_moe":true,"num_experts":384},"parameter_count":"1026.5B","parameters_raw":1026470735448,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-09-03","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2-Instruct-0905","knowledge":"2024-10","last_updated":"2025-09-04","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi-K2-Instruct-0905","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"moonshotai/Kimi-K2-Thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.6,"output":2.5},"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":"huggingface","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":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.5","knowledge":"2025-01","last_updated":"2026-01-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi-K2.5","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-01-01","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"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","video"],"output":["text"]},"model":null,"name":"Kimi-K2.6","pricing":null,"provider":"huggingface","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":{"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/Kimi-K3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/Kimi-K3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.69},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"huggingface","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":{"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-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"]}],"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":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"stepfun-ai/Step-3.5-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","llmfit":{"architecture":"step3p5","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/Step-3.5-Flash-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Step-3.5-Flash-GGUF"}],"hf_downloads":94390,"hf_likes":829,"matched_hugging_face_id":"stepfun-ai/Step-3.5-Flash","memory":{"min_ram_gb":111.4,"min_vram_gb":102.1,"recommended_ram_gb":185.7},"model_id":"stepfun-ai/Step-3.5-Flash","parameter_count":"199.4B","parameters_raw":199384301376,"pipeline_tag":"text-generation","provider":"stepfun-ai","quantization":"Q4_K_M","release_date":"2026-02-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"stepfun-ai/Step-3.5-Flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Step 3.5 Flash","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"stepfun-ai/Step-3.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","llmfit":{"architecture":"step3p7","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Step-3.7-Flash-GGUF"},{"provider":"bartowski","repo":"bartowski/Step-3.7-Flash-GGUF"}],"hf_downloads":143509,"hf_likes":0,"matched_hugging_face_id":"stepfun-ai/Step-3.7-Flash","memory":{"min_ram_gb":112.5,"min_vram_gb":103.1,"recommended_ram_gb":187.5},"model_id":"stepfun-ai/Step-3.7-Flash","parameter_count":"201.4B","parameters_raw":201365316160,"pipeline_tag":"image-text-to-text","provider":"stepfun-ai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"stepfun-ai/Step-3.7-Flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"tencent/Hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":23137,"hf_likes":0,"matched_hugging_face_id":"tencent/Hy3","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"tencent/Hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"ling","llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":65012,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling","memory":{"min_ram_gb":532.2,"min_vram_gb":487.8,"recommended_ram_gb":887.0},"model_id":"thinkingmachines/Inkling","moe":{"active_experts":6,"active_parameters":68824164203,"is_moe":true,"num_experts":256},"parameter_count":"952.4B","parameters_raw":952377623626,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/Inkling-Small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"thinkingmachines/Inkling-Small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"zai-org/GLM-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-GGUF"}],"hf_downloads":123213,"hf_likes":1408,"matched_hugging_face_id":"zai-org/GLM-4.5","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.5","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":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-4.5-Air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.85},"deprecated":false,"extra":{"attachment":false,"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-Air-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5-Air-GGUF"}],"hf_downloads":441341,"hf_likes":625,"matched_hugging_face_id":"zai-org/GLM-4.5-Air","memory":{"min_ram_gb":61.7,"min_vram_gb":56.6,"recommended_ram_gb":102.9},"model_id":"zai-org/GLM-4.5-Air","moe":{"active_experts":8,"active_parameters":12082527713,"is_moe":true,"num_experts":128},"parameter_count":"110.5B","parameters_raw":110468824832,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.5-Air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5-Air","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai-org/GLM-4.5V":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","llmfit":{"architecture":"glm4v_moe","context_length":65536,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/GLM-4.5V-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5V-GGUF"}],"hf_downloads":146121,"hf_likes":0,"matched_hugging_face_id":"zai-org/GLM-4.5V","memory":{"min_ram_gb":60.2,"min_vram_gb":55.2,"recommended_ram_gb":100.3},"model_id":"zai-org/GLM-4.5V","moe":{"active_experts":8,"active_parameters":11780883304,"is_moe":true,"num_experts":128},"parameter_count":"107.7B","parameters_raw":107710933120,"pipeline_tag":"image-text-to-text","provider":"zai-org","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.5V","knowledge":"2025-04","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM-4.5V","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-08-11","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":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":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":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"huggingface","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":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai-org/GLM-4.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"glm4_moe_lite","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":2074814,"hf_likes":1800,"matched_hugging_face_id":"zai-org/GLM-4.7-Flash","memory":{"min_ram_gb":17.4,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"zai-org/GLM-4.7-Flash","moe":{"active_experts":4,"active_parameters":3414850312,"is_moe":true,"num_experts":64},"parameter_count":"31.2B","parameters_raw":31221488576,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-01-19","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"zai-org/GLM-4.7-Flash","knowledge":"2025-04","last_updated":"2025-08-08","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2025-08-08","retired":false,"tags":null},"zai-org/GLM-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"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":[],"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":"huggingface","provider_model_id":null,"release_date":"2026-02-11","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":0.2,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"llmfit":{"architecture":"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":[],"temperature":true},"family":null,"id":"zai-org/GLM-5.1","knowledge":null,"last_updated":"2026-04-03","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"zai-org/GLM-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","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":[],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/GLM-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"huggingface","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"Hugging Face","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/hyper.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "hyper",
+  "deepseek-v4-flash" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "gemma-4-26b-a4b-it" | "glm-5" | "glm-5.1" | "glm-5.2" | "gpt-oss-120b" | "kimi-k2.5" | "kimi-k2.6" | "kimi-k2.7-code" | "kimi-k3" | "llama-3.3-70b-instruct" | "llama-4-maverick-17b-128e-instruct-fp8" | "minimax-m2.7" | "minimax-m3" | "qwen3-coder-480b-a35b-instruct-int4-mixed-ar" | "qwen3-next-80b-a3b-instruct" | "qwen3.6-flash" | "qwen3.6-max" | "qwen3.6-plus" | "qwen3.7-flash" | "qwen3.7-max" | "qwen3.7-plus" | "qwen3.8-max"
+>;
+export default provider;

package/dist/providers/hyper.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://hyper.charm.land/v1","catalog_only":true,"config_schema":null,"doc":"https://hyper.charm.land","env":["HYPER_API_KEY"],"exclude_models":null,"extra":null,"id":"hyper","models":{"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":0.04,"input":0.2,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"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":0.032664,"input":0.152432,"output":0.304864},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-08-02","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-08-02","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":0.2,"input":2.4,"output":4.8},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"gemma-4-26b-a4b-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_write":0.063,"input":0.126,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":256000,"output":25600},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.425,"input":0.85,"output":2.622},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-5","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":202752,"output":20275},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-13","retired":false,"tags":null},"glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.283088,"input":1.52432,"output":4.79072},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":202800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-06-04","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":0.28,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.094,"input":0.188,"output":0.7},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":131072,"output":13107},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-13","retired":false,"tags":null},"kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.27,"input":0.54,"output":2.85},"deprecated":false,"extra":{"attachment":false,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":262144,"output":26214},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-13","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_write":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-03","retired":false,"tags":null},"kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":256000,"output":16000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-03","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.32664,"input":3.2664,"output":16.332},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"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_write":0.2563,"input":0.5126,"output":1.0446},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":128000,"output":12800},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"llama-4-maverick-17b-128e-instruct-fp8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.142,"input":0.284,"output":0.934},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-4-maverick-17b-128e-instruct-fp8","knowledge":"2024-08","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":430000,"output":43000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B Instruct","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"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":{"cache_write":0.21,"input":0.42,"output":1.62},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.7","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":262100,"output":6553},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-06-05","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":0.064239,"input":0.32664,"output":1.30656},"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":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m3","knowledge":null,"last_updated":"2026-07-31","lifecycle":null,"limits":{"context":512000,"output":512000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"qwen3-coder-480b-a35b-instruct-int4-mixed-ar":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.2875,"input":0.575,"output":2.145},"deprecated":false,"extra":{"attachment":false,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-480b-a35b-instruct-int4-mixed-ar","knowledge":"2025-04","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":106000,"output":10600},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 480B-A35B Instruct","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_write":0.05875,"input":0.1175,"output":1.136},"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":"qwen3-next-80b-a3b-instruct","knowledge":"2025-04","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":262144,"output":26214},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B Instruct","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"qwen3.6-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":0.1,"cache_write":1.25,"input":1,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-flash","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 Flash","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"qwen3.6-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":0.2,"cache_write":2.5,"input":2,"output":12},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.6-max","knowledge":"2025-04","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 Max Preview","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"qwen3.6-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":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"qwen3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.7-flash","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.7 Flash","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"qwen3.7-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":0.5,"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.7-max","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"qwen3.7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4.8},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-07-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-06-15","retired":false,"tags":null},"qwen3.8-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":0.25,"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.8-max","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.8 Max Preview","pricing":null,"provider":"hyper","provider_model_id":null,"release_date":"2026-07-19","retired":false,"tags":null}},"name":"Charm Hyper","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/iflowcn.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "iflowcn",
+  "deepseek-r1" | "deepseek-v3" | "deepseek-v3.2" | "glm-4.6" | "kimi-k2" | "kimi-k2-0905" | "qwen3-235b" | "qwen3-235b-a22b-instruct" | "qwen3-235b-a22b-thinking-2507" | "qwen3-32b" | "qwen3-coder-plus" | "qwen3-max" | "qwen3-max-preview" | "qwen3-vl-plus"
+>;
+export default provider;

package/dist/providers/iflowcn.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://apis.iflow.cn/v1","catalog_only":true,"config_schema":null,"doc":"https://platform.iflow.cn/en/docs","env":["IFLOW_API_KEY"],"exclude_models":null,"extra":null,"id":"iflowcn","models":{"deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-r1","knowledge":"2024-12","last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-v3":{"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":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-v3","knowledge":"2024-10","last_updated":"2024-12-26","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"temperature":true},"family":null,"id":"deepseek-v3.2","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.2-Exp","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"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,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-4.6","knowledge":"2024-10","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"kimi-k2":{"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":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi-K2","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"kimi-k2-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-0905","knowledge":"2024-12","last_updated":"2025-09-05","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi-K2-0905","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-09-05","retired":false,"tags":null},"qwen3-235b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-235b","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"qwen3-235b-a22b-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,"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":"qwen3-235b-a22b-instruct","knowledge":"2025-04","last_updated":"2025-07-01","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B-Instruct","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-235b-a22b-thinking-2507","knowledge":"2025-04","last_updated":"2025-07-01","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-235B-A22B-Thinking","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"qwen3-32b":{"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":"qwen3-32b","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-32B","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"qwen3-coder-plus":{"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":"qwen3-coder-plus","knowledge":"2025-04","last_updated":"2025-07-01","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder-Plus","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-07-01","retired":false,"tags":null},"qwen3-max":{"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":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-max","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Max","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen3-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-max-preview","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Max-Preview","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen3-vl-plus":{"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":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-vl-plus","knowledge":"2024-12","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3-VL-Plus","pricing":null,"provider":"iflowcn","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null}},"name":"iFlow","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;