Danh mục Model AI đa nhà cung cấp
Siêu dữ liệu độc lập nhà cung cấp kèm nguồn gốc giá rõ ràng, cảnh báo dữ liệu cũ, context window và yêu cầu phần cứng cục bộ.
Tự động đồng bộ nền từ OpenRouter & HuggingFace theo lịch máy chủ, tuyệt đối không ghi đè dữ liệu giá đã xác minh.
Snapshot 2026-11-21-live · 13 Provider Sources · 187 Deduplicated Models
Universal Model Catalog
Extensible multi-source registry with verified pricing provenance, context limits, local hardware requirements, and deprecation flags. Select up to 4 models to compare side by side.
| Cmp | Model & Capabilities | Deployment | Context | Input / Output ($/1M) | Pricing Source & Status |
|---|---|---|---|---|---|
AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP4-MTP huggingface/automatosx-ax-qwen3.5-0.8b-decision-mlx-axq-mxfp4-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP4-MTP | |
AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP8-MTP huggingface/automatosx-ax-qwen3.5-0.8b-decision-mlx-axq-mxfp8-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP8-MTP | |
AX-Qwen3.5-9B-MLX-AXQ-6bit-MTP huggingface/automatosx-ax-qwen3.5-9b-mlx-axq-6bit-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-6bit-MTP | |
AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP huggingface/automatosx-ax-qwen3.5-9b-mlx-axq-mxfp4-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP | |
AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP huggingface/automatosx-ax-qwen3.5-9b-mlx-axq-mxfp8-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP | |
AX-Qwen3.6-27B-MLX-AXQ-6bit-MTP huggingface/automatosx-ax-qwen3.6-27b-mlx-axq-6bit-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit-MTP | |
AX-Qwen3.6-35B-A3B-MLX-AXQ-6bit-MTP huggingface/automatosx-ax-qwen3.6-35b-a3b-mlx-axq-6bit-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-6bit-MTP | |
AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP huggingface/automatosx-ax-qwen3.6-35b-a3b-mlx-axq-mxfp4-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP | |
AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP huggingface/automatosx-ax-qwen3.6-35b-a3b-mlx-axq-mxfp8-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP | |
AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP huggingface/automatosx-ax-qwen3.8-27b-mlx-axq-mxfp4-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP | |
AX-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP huggingface/automatosx-ax-qwen3.8-27b-mlx-axq-mxfp8-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP | |
AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-6bit-MTP huggingface/automatosx-ax-swift-1.5-qwen3.8-27b-mlx-axq-6bit-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-6bit-MTP | |
AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP huggingface/automatosx-ax-swift-1.5-qwen3.8-27b-mlx-axq-mxfp4-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP | |
AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP huggingface/automatosx-ax-swift-1.5-qwen3.8-27b-mlx-axq-mxfp8-mtp · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP | |
Claude 3.5 Haiku claude-3-5-haiku · Anthropic coding · tool_calling · structured_output · long_context | cloud Direct API | 200k | $0.80 / $4.00 | verified · 2026-11-10 https://docs.anthropic.com/en/docs/about-claude/models/overview | |
Claude Fable 5.2 anthropic/claude-fable-5.2 · Anthropic reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $8.00 / $40.00 | provider reported · 2026-11-09 https://openrouter.ai/models | |
Claude Haiku 5.5 anthropic/claude-haiku-5.5 · Anthropic reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.10 / $0.50 | provider reported · 2026-10-07 https://openrouter.ai/models | |
Claude Opus 5.5 anthropic/claude-opus-5.5 · Anthropic coding · reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $4.00 / $20.00 | provider reported · 2026-09-22 https://openrouter.ai/models | |
Claude Sonnet 4.5 claude-sonnet-4-5 · Anthropic coding · reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 200k | $3.00 / $15.00 | verified · 2026-11-10 https://docs.anthropic.com/en/docs/about-claude/models/overview | |
Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 · Anthropic coding · reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-09-28 https://openrouter.ai/models | |
Codestral 25.01 codestral-2501 · Mistral AI coding · structured_output · long_context | cloud Direct API | 256k | $0.30 / $0.90 | provider reported · 2026-10-20 https://mistral.ai/pricing | |
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash · DeepSeek coding · reasoning · vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $0.05 / $0.20 | provider reported · 2026-09-10 Stale or unverified pricing https://openrouter.ai/models | |
DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 · DeepSeek coding · reasoning · vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $0.15 / $0.60 | provider reported · 2026-10-17 https://openrouter.ai/models | |
DeepSeek-Prover-V2-7B-GGUF huggingface/42ailab-deepseek-prover-v2-7b-gguf · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/42ailab/DeepSeek-Prover-V2-7B-GGUF | |
DeepSeek-R1 deepseek-r1 · DeepSeek coding · reasoning · structured_output | both 32GB+ RAM | 128k | $0.55 / $2.19 | provider reported · 2026-11-05 https://api-docs.deepseek.com/quick_start/pricing | |
DeepSeek-R1-Distill-Qwen-1.5B-SGNE-CC-v2 huggingface/nondual-observer-deepseek-r1-distill-qwen-1.5b-sgne-cc-v2 · Qwen tool_calling · structured_output · reasoning | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Nondual-Observer/DeepSeek-R1-Distill-Qwen-1.5B-SGNE-CC-v2 | |
DeepSeek-V3 deepseek-v3 · DeepSeek coding · tool_calling · structured_output | cloud Direct API | 128k | $0.27 / $1.10 | provider reported · 2026-11-05 https://api-docs.deepseek.com/quick_start/pricing | |
DeepSeek-V4-Flash huggingface/xgyubnkl-deepseek-v4-flash · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/XGYUBNKL/DeepSeek-V4-Flash | |
DeepSeek-V4-Flash-0731-MaxQ-v4-64GB-CPU-GGUF huggingface/synchopate-deepseek-v4-flash-0731-maxq-v4-64gb-cpu-gguf · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Synchopate/DeepSeek-V4-Flash-0731-MaxQ-v4-64GB-CPU-GGUF | |
DeepSeek-V4-Pro huggingface/pd584-deepseek-v4-pro · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/pd584/DeepSeek-V4-Pro | |
DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic huggingface/aaaaygd-deepseek-v4-pro-qwen3.5-4b-uncensored-heretic · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/aaaaygd/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic | |
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic huggingface/xsyh1-deepseek-v4-pro-qwen3.5-9b-uncensored-heretic · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/xsyh1/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic | |
DeepSeek-V4.1-Flash-1017-GGUF huggingface/flaviodelgrosso-deepseek-v4.1-flash-1017-gguf · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/flaviodelgrosso/DeepSeek-V4.1-Flash-1017-GGUF | |
DeepSeek-V4.1-Flash-1017-obliterated-MLX-oQ2.5e huggingface/pocketaihub-deepseek-v4.1-flash-1017-obliterated-mlx-oq2.5e · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/PocketAiHub/DeepSeek-V4.1-Flash-1017-obliterated-MLX-oQ2.5e | |
DeepSeek-V4.1-Flash-1017-Uncensored huggingface/openuncensored-deepseek-v4.1-flash-1017-uncensored · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/OpenUncensored/DeepSeek-V4.1-Flash-1017-Uncensored | |
dolphin-2.6-mixtral-8x7b huggingface/dphn-dolphin-2.6-mixtral-8x7b · Mistral AI tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/dolphin-2.6-mixtral-8x7b | |
dolphin-2.8-gemma-2b huggingface/dphn-dolphin-2.8-gemma-2b · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/dolphin-2.8-gemma-2b | |
dolphin-2.8-gemma-7b huggingface/dphn-dolphin-2.8-gemma-7b · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/dolphin-2.8-gemma-7b | |
dolphin-2.9.1-llama-3-70b huggingface/dphn-dolphin-2.9.1-llama-3-70b · Meta / Llama tool_calling · structured_output | local 48GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/dolphin-2.9.1-llama-3-70b | |
dolphin-2.9.3-mistral-nemo-12b huggingface/dphn-dolphin-2.9.3-mistral-nemo-12b · Mistral AI tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/dolphin-2.9.3-mistral-nemo-12b | |
Dolphin3.0-Mistral-24B huggingface/dphn-dolphin3.0-mistral-24b · Mistral AI tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/Dolphin3.0-Mistral-24B | |
Dolphin3.0-R1-Mistral-24B huggingface/dphn-dolphin3.0-r1-mistral-24b · Mistral AI tool_calling · structured_output · reasoning | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dphn/Dolphin3.0-R1-Mistral-24B | |
einsof2-deepseek-prover-v2-stiefel-gguf huggingface/polydim-einsof-einsof2-deepseek-prover-v2-stiefel-gguf · DeepSeek tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Polydim-Einsof/einsof2-deepseek-prover-v2-stiefel-gguf | |
flexing-v1-based-qwen2.5coder huggingface/lahyk-flexing-v1-based-qwen2.5coder · Qwen coding · tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/lahyk/flexing-v1-based-qwen2.5coder | |
Gemini 2.5 Flash gemini-2.5-flash · Google Gemini coding · reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.30 / $2.50 | verified · 2026-11-14 https://ai.google.dev/gemini-api/docs/pricing | |
Gemini 2.5 Pro gemini-2.5-pro · Google Gemini coding · reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $1.25 / $10.00 | verified · 2026-11-14 https://ai.google.dev/gemini-api/docs/pricing | |
Gemini 3.8 Flash google_gemini/gemini-3.8-flash · Google Gemini coding · reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.82 / $4.13 | provider reported · 2026-09-02 Stale or unverified pricing https://openrouter.ai/models | |
Gemini 4 Argon google_gemini/gemini-4-argon · Google Gemini reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-10-13 https://openrouter.ai/models | |
Gemini 4 Carbon google_gemini/gemini-4-carbon · Google Gemini reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-11-10 https://openrouter.ai/models | |
Gemini 4 Hydrogen google_gemini/gemini-4-hydrogen · Google Gemini reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $1.50 / $7.50 | provider reported · 2026-11-12 https://openrouter.ai/models | |
Gemini 4 Neon google_gemini/gemini-4-neon · Google Gemini reasoning · vision · audio · tool_calling · structured_output · long_context | cloud Direct API | 1M | $3.00 / $15.00 | provider reported · 2026-11-18 https://openrouter.ai/models | |
Gemini Omni 1.1 Flash google_gemini/gemini-omni-1.1-flash · Google Gemini reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 131k | $1.50 / $9.00 | provider reported · 2026-11-04 https://openrouter.ai/models | |
Gemini Omni 1.2 Flash google_gemini/gemini-omni-1.2-flash · Google Gemini reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 131k | $1.50 / $9.00 | provider reported · 2026-11-05 https://openrouter.ai/models | |
gemma-3-0.8b-csw huggingface/aletheiaaing-gemma-3-0.8b-csw · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/AletheiaAING/gemma-3-0.8b-csw | |
gemma-3-1b-csw-best huggingface/aletheiaaing-gemma-3-1b-csw-best · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best | |
gemma-3-1b-csw-best-pruned huggingface/aletheiaaing-gemma-3-1b-csw-best-pruned · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best-pruned | |
gemma-3-1b-csw-best-pruned-fp8 huggingface/aletheiaaing-gemma-3-1b-csw-best-pruned-fp8 · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best-pruned-fp8 | |
gemma-3-1b-csw-sft huggingface/aletheiaaing-gemma-3-1b-csw-sft · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/AletheiaAING/gemma-3-1b-csw-sft | |
gemma-3-270m-it-food-extract huggingface/bhai2000-gemma-3-270m-it-food-extract · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/bhai2000/gemma-3-270m-it-food-extract | |
gemma-4-12B-penguin huggingface/glyd-gemma-4-12b-penguin · Google Gemini tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/glyd/gemma-4-12B-penguin | |
gemma-4-12B-wren huggingface/glyd-gemma-4-12b-wren · Google Gemini tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/glyd/gemma-4-12B-wren | |
gemma-4-31B-penguin huggingface/glyd-gemma-4-31b-penguin · Google Gemini tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/glyd/gemma-4-31B-penguin | |
gemma-4-31B-wren huggingface/glyd-gemma-4-31b-wren · Google Gemini tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/glyd/gemma-4-31B-wren | |
Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF huggingface/mradermacher-gemma-4-e2b-it-ara-abliterated-i1-gguf · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/mradermacher/Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF | |
gemma-4-E2B-it-GGUF huggingface/xylolabs-gemma-4-e2b-it-gguf · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Xylolabs/gemma-4-E2B-it-GGUF | |
Gemma-4-E2B-LokalBot-GGUF huggingface/stevyhacker-gemma-4-e2b-lokalbot-gguf · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/stevyhacker/Gemma-4-E2B-LokalBot-GGUF | |
gemma-4-E4B-it-GGUF huggingface/xylolabs-gemma-4-e4b-it-gguf · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Xylolabs/gemma-4-E4B-it-GGUF | |
GLM-5.3-Flash-numallama huggingface/miloserdev-glm-5.3-flash-numallama · Meta / Llama coding · tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/miloserdev/GLM-5.3-Flash-numallama | |
GPT-4.1 gpt-4.1 · OpenAI coding · reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $8.00 | verified · 2026-11-12 https://openai.com/api/pricing/ | |
GPT-4.1 mini gpt-4.1-mini · OpenAI coding · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.40 / $1.60 | verified · 2026-11-12 https://openai.com/api/pricing/ | |
GPT-6 Astra openai/gpt-6-astra · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $10.00 / $50.00 | provider reported · 2026-09-04 Stale or unverified pricing https://openrouter.ai/models | |
GPT-6 Astra Pro openai/gpt-6-astra-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $10.00 / $50.00 | provider reported · 2026-09-04 Stale or unverified pricing https://openrouter.ai/models | |
GPT-6 Luna openai/gpt-6-luna · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.10 / $0.50 | provider reported · 2026-09-22 https://openrouter.ai/models | |
GPT-6 Luna Pro openai/gpt-6-luna-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.10 / $0.50 | provider reported · 2026-09-22 https://openrouter.ai/models | |
GPT-6 Sol openai/gpt-6-sol · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-09-22 https://openrouter.ai/models | |
GPT-6 Sol Pro openai/gpt-6-sol-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-09-22 https://openrouter.ai/models | |
GPT-6.1 Sol openai/gpt-6.1-sol · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-09-29 https://openrouter.ai/models | |
GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-09-29 https://openrouter.ai/models | |
GPT-6.1 Terra openai/gpt-6.1-terra · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $1.00 / $5.00 | provider reported · 2026-10-26 https://openrouter.ai/models | |
GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $1.00 / $5.00 | provider reported · 2026-10-26 https://openrouter.ai/models | |
GPT-6.2 Astra openai/gpt-6.2-astra · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $8.00 / $40.00 | provider reported · 2026-11-17 https://openrouter.ai/models | |
GPT-6.2 Astra Pro openai/gpt-6.2-astra-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $8.00 / $40.00 | provider reported · 2026-11-17 https://openrouter.ai/models | |
GPT-6.2 Sol openai/gpt-6.2-sol · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-11-17 https://openrouter.ai/models | |
GPT-6.2 Sol Pro openai/gpt-6.2-sol-pro · OpenAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $2.00 / $10.00 | provider reported · 2026-11-17 https://openrouter.ai/models | |
GPT-Distill-Qwen3-8B-Spellguard-SLERP huggingface/itll-gpt-distill-qwen3-8b-spellguard-slerp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/ITLL/GPT-Distill-Qwen3-8B-Spellguard-SLERP | |
Grok 3 grok-3 · xAI coding · reasoning · tool_calling · structured_output | cloud Direct API | 131k | $3.00 / $15.00 | provider reported · 2026-10-28 https://docs.x.ai/docs/models | |
Grok 4.7 xai/grok-4.7 · xAI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 500k | $2.00 / $6.00 | provider reported · 2026-09-21 https://openrouter.ai/models | |
JiRackGemma-37B-alpha-GGUF huggingface/cmsmanhattan-jirackgemma-37b-alpha-gguf · Google Gemini tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/CMSManhattan/JiRackGemma-37B-alpha-GGUF | |
JiRackGemma-72B-alpha-GGUF huggingface/cmsmanhattan-jirackgemma-72b-alpha-gguf · Google Gemini tool_calling · structured_output | local 48GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/CMSManhattan/JiRackGemma-72B-alpha-GGUF | |
Llama 3.3 70B Instruct llama-3.3-70b-instruct · Meta / Llama coding · reasoning · tool_calling · structured_output | both 48GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-10 Local open-weight execution ($0 API fee); hosted pricing varies by provider | |
Llama-3.1-8B-Instruct-InWeight-FPGA-WSP huggingface/masstensor-llama-3.1-8b-instruct-inweight-fpga-wsp · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/masstensor/Llama-3.1-8B-Instruct-InWeight-FPGA-WSP | |
Llama-3.1-8B-Instruct-InWeight-OS huggingface/masstensor-llama-3.1-8b-instruct-inweight-os · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/masstensor/Llama-3.1-8B-Instruct-InWeight-OS | |
llama-3.2-3b-abliterated huggingface/lecheyne24-llama-3.2-3b-abliterated · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lecheyne24/llama-3.2-3b-abliterated | |
Llama-3.2-3B-Alpaca-ID-GRPO huggingface/jeffrymahbuubi-llama-3.2-3b-alpaca-id-grpo · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/jeffrymahbuubi/Llama-3.2-3B-Alpaca-ID-GRPO | |
Llama-4-Scout-17B-16E-Instruct huggingface/litert-community-llama-4-scout-17b-16e-instruct · Meta / Llama tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/litert-community/Llama-4-Scout-17B-16E-Instruct | |
llama3-8b-instruct-med-math-della-k10 huggingface/shahriarferdoush-llama3-8b-instruct-med-math-della-k10 · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/ShahriarFerdoush/llama3-8b-instruct-med-math-della-k10 | |
llama3-8b-instruct-med-math-pcb-k10 huggingface/shahriarferdoush-llama3-8b-instruct-med-math-pcb-k10 · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/ShahriarFerdoush/llama3-8b-instruct-med-math-pcb-k10 | |
llm2026-g6-ctrl-legacy-qwen35-08b huggingface/kanippa-llm2026-g6-ctrl-legacy-qwen35-08b · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/kanippa/llm2026-g6-ctrl-legacy-qwen35-08b | |
Mistral Large 4 mistral/mistral-large-4-0 · Mistral AI reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 1M | $0.70 / $2.10 | provider reported · 2026-10-06 https://openrouter.ai/models | |
Mistral Small 3 24B (Community Preview) mistral-small-3-24b-instruct · Hugging Face coding · tool_calling · structured_output | both 16GB+ RAM | 33k | Unknown | unknown · Unverified Stale or unverified pricing Unverified — hosted API pricing not published by source | |
mistral-7b-abliterated huggingface/lecheyne24-mistral-7b-abliterated · Mistral AI tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lecheyne24/mistral-7b-abliterated | |
mistral-nemo-12b-abliterated huggingface/lecheyne24-mistral-nemo-12b-abliterated · Mistral AI tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lecheyne24/mistral-nemo-12b-abliterated | |
Nano Banana 2.1 google_gemini/gemini-nano-banana-2.1 · Google Gemini reasoning · vision · tool_calling · structured_output | cloud Direct API | 66k | $1.50 / $7.50 | provider reported · 2026-10-06 https://openrouter.ai/models | |
Nazo-Qwen3-4B-Thinking-2507 huggingface/nassimjp-nazo-qwen3-4b-thinking-2507 · Qwen tool_calling · structured_output · reasoning | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/nassimjp/Nazo-Qwen3-4B-Thinking-2507 | |
Nous-Hermes-Llama2-13b-Storywriter-GGUF huggingface/mradermacher-nous-hermes-llama2-13b-storywriter-gguf · Meta / Llama tool_calling · structured_output | local 16GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/mradermacher/Nous-Hermes-Llama2-13b-Storywriter-GGUF | |
OpenAI o3 o3 · OpenAI coding · reasoning · vision · tool_calling · structured_output · long_context | cloud Direct API | 200k | $2.00 / $8.00 | verified · 2026-11-12 https://openai.com/api/pricing/ | |
Pakistani_legal_Qwen3b_8b huggingface/mohsin245-pakistani_legal_qwen3b_8b · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Mohsin245/Pakistani_legal_Qwen3b_8b | |
phi-4-GGUF huggingface/xylolabs-phi-4-gguf · Hugging Face tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/phi-4-GGUF | |
Pixtral Large 2502 mistral/pixtral-large-2502 · Mistral AI vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 128k | $2.00 / $6.00 | provider reported · 2026-11-20 https://openrouter.ai/models | |
Qwen 2.5 Coder 32B (Local) qwen2.5-coder-32b-instruct · Qwen coding · tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | verified · 2026-11-15 Local open-weight execution (hardware electricity only; $0 API fee) | |
Qwen 2.5 Coder 7B (Laptop Local) qwen2.5-coder-7b-instruct · Ollama coding · tool_calling · structured_output | local 8GB+ RAM | 33k | $0.00 / $0.00 | verified · 2026-11-15 Local open-weight execution ($0 API fee) | |
Qwen Max (Model Studio) qwen-max · Alibaba Cloud coding · reasoning · tool_calling · structured_output | cloud Direct API | 131k | $1.60 / $6.40 | provider reported · 2026-08-01 Stale or unverified pricing https://www.alibabacloud.com/help/en/model-studio/models | |
Qwen-3.8-9B-Uncensored-Heretic-Ch-Enhanced-V1-GGUF huggingface/alex500-qwen-3.8-9b-uncensored-heretic-ch-enhanced-v1-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Alex500/Qwen-3.8-9B-Uncensored-Heretic-Ch-Enhanced-V1-GGUF | |
qwen-code-dpo huggingface/lalit63-qwen-code-dpo · Qwen coding · tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lalit63/qwen-code-dpo | |
Qwen-VL huggingface/png79-qwen-vl · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/PNG79/Qwen-VL | |
qwen2.5-0.5b-instruct-abliterated huggingface/lukefrazier23-qwen2.5-0.5b-instruct-abliterated · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/LukeFrazier23/qwen2.5-0.5b-instruct-abliterated | |
qwen2.5-3b-abliterated huggingface/lecheyne24-qwen2.5-3b-abliterated · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lecheyne24/qwen2.5-3b-abliterated | |
qwen2.5-coder-7b-abliterated huggingface/lecheyne24-qwen2.5-coder-7b-abliterated · Qwen coding · tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/lecheyne24/qwen2.5-coder-7b-abliterated | |
Qwen3-0.6B-Q4_K_M-GGUF huggingface/jffernandez26-qwen3-0.6b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/jffernandez26/Qwen3-0.6B-Q4_K_M-GGUF | |
Qwen3-0.6B-Q4_K_M-GGUF huggingface/s1l53r-qwen3-0.6b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/S1L53R/Qwen3-0.6B-Q4_K_M-GGUF | |
Qwen3-0.6B-Q8_0-GGUF huggingface/jffernandez26-qwen3-0.6b-q8_0-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/jffernandez26/Qwen3-0.6B-Q8_0-GGUF | |
qwen3-1.7b-gguf huggingface/timdedid-qwen3-1.7b-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/timdedid/qwen3-1.7b-gguf | |
Qwen3-1.7B-Q4_K_M-GGUF huggingface/693448manu-qwen3-1.7b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/693448Manu/Qwen3-1.7B-Q4_K_M-GGUF | |
Qwen3-1.7B-Q4_K_M-GGUF huggingface/aguilar82-qwen3-1.7b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Aguilar82/Qwen3-1.7B-Q4_K_M-GGUF | |
Qwen3-1.7B-Q4_K_M-GGUF huggingface/carlosveru-qwen3-1.7b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/CarlosVeRu/Qwen3-1.7B-Q4_K_M-GGUF | |
Qwen3-1.7B-Q4_K_M-GGUF huggingface/david0101011-qwen3-1.7b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/David0101011/Qwen3-1.7B-Q4_K_M-GGUF | |
Qwen3-1.7B-Q4_K_M-GGUF huggingface/frank815-qwen3-1.7b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Frank815/Qwen3-1.7B-Q4_K_M-GGUF | |
Qwen3-1.7B-Q8_0-GGUF huggingface/frank815-qwen3-1.7b-q8_0-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Frank815/Qwen3-1.7B-Q8_0-GGUF | |
Qwen3-30B-A3B-Instruct-2507-NVFP4A16 huggingface/puretensor-qwen3-30b-a3b-instruct-2507-nvfp4a16 · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16 | |
Qwen3-30B-A3B-Instruct-2507-NVFP4A16-ExpertsOnly huggingface/puretensor-qwen3-30b-a3b-instruct-2507-nvfp4a16-expertsonly · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16-ExpertsOnly | |
qwen3-4b-medQA-kklang huggingface/darynel-qwen3-4b-medqa-kklang · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/dARYNel/qwen3-4b-medQA-kklang | |
Qwen3-4B-Q4_K_M-GGUF huggingface/rafaalu-qwen3-4b-q4_k_m-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/RafaAlu/Qwen3-4B-Q4_K_M-GGUF | |
qwen3-4b-toolcall-dpo-awq-w4a16 huggingface/arman-52-qwen3-4b-toolcall-dpo-awq-w4a16 · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/arman-52/qwen3-4b-toolcall-dpo-awq-w4a16 | |
qwen3-4b-toolcall-dpo-merged huggingface/arman-52-qwen3-4b-toolcall-dpo-merged · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/arman-52/qwen3-4b-toolcall-dpo-merged | |
Qwen3-8B-GGUF huggingface/xylolabs-qwen3-8b-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/Qwen3-8B-GGUF | |
Qwen3-8B-InWeight-FPGA-WSP huggingface/masstensor-qwen3-8b-inweight-fpga-wsp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP | |
Qwen3-8B-InWeight-OS huggingface/masstensor-qwen3-8b-inweight-os · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/masstensor/Qwen3-8B-InWeight-OS | |
qwen3-8b-pmtp huggingface/polydim-einsof-qwen3-8b-pmtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Polydim-Einsof/qwen3-8b-pmtp | |
qwen3-cyber-UNCENSORED huggingface/timdedid-qwen3-cyber-uncensored · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/timdedid/qwen3-cyber-UNCENSORED | |
Qwen3.5-0.8B huggingface/litert-community-qwen3.5-0.8b · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/litert-community/Qwen3.5-0.8B | |
Qwen3.5-0.8B-Persian-Agent huggingface/mohammadbeigi-qwen3.5-0.8b-persian-agent · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/MohammadBeigi/Qwen3.5-0.8B-Persian-Agent | |
Qwen3.5-0.8B-Persian-Agent-GGUF huggingface/mohammadbeigi-qwen3.5-0.8b-persian-agent-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/MohammadBeigi/Qwen3.5-0.8B-Persian-Agent-GGUF | |
Qwen3.5-2B-GGUF huggingface/42ailab-qwen3.5-2b-gguf · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/42ailab/Qwen3.5-2B-GGUF | |
qwen3.5-2b-gym-grpo-GGUF huggingface/riccardoroselli-qwen3.5-2b-gym-grpo-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/riccardoroselli/qwen3.5-2b-gym-grpo-GGUF | |
Qwen3.5-4B-Base-GGUF huggingface/xylolabs-qwen3.5-4b-base-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/Qwen3.5-4B-Base-GGUF | |
Qwen3.5-4B-GGUF huggingface/42ailab-qwen3.5-4b-gguf · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/42ailab/Qwen3.5-4B-GGUF | |
Qwen3.5-4B-GGUF huggingface/xylolabs-qwen3.5-4b-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/Qwen3.5-4B-GGUF | |
Qwen3.5-9B-Base-GGUF huggingface/xylolabs-qwen3.5-9b-base-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/Qwen3.5-9B-Base-GGUF | |
Qwen3.5-9B-GGUF huggingface/42ailab-qwen3.5-9b-gguf · Qwen tool_calling · structured_output · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/42ailab/Qwen3.5-9B-GGUF | |
Qwen3.5-9B-GGUF huggingface/xylolabs-qwen3.5-9b-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Xylolabs/Qwen3.5-9B-GGUF | |
Qwen3.5-9B-XeFP4 huggingface/kinoq-qwen3.5-9b-xefp4 · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/KINOQ/Qwen3.5-9B-XeFP4 | |
Qwen3.6-35B-A3B-Fable-5-Distill-heretic-i1-GGUF huggingface/mradermacher-qwen3.6-35b-a3b-fable-5-distill-heretic-i1-gguf · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/mradermacher/Qwen3.6-35B-A3B-Fable-5-Distill-heretic-i1-GGUF | |
Qwen3.6-35B-A3B-TR2.25-G-GGUF huggingface/ternii-qwen3.6-35b-a3b-tr2.25-g-gguf · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Ternii/Qwen3.6-35B-A3B-TR2.25-G-GGUF | |
Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 · Qwen reasoning · vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $2.00 / $6.00 | provider reported · 2026-09-03 Stale or unverified pricing https://openrouter.ai/models | |
Qwen3.8 Max Prime qwen/qwen3.8-max-prime · Qwen reasoning · vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $4.00 / $12.00 | provider reported · 2026-09-23 https://openrouter.ai/models | |
Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash · Qwen reasoning · vision · audio · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $0.15 / $0.47 | provider reported · 2026-09-21 https://openrouter.ai/models | |
Qwen3.8-2.4T-A95B huggingface/cradia-qwen3.8-2.4t-a95b · Qwen tool_calling · structured_output | local 48GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Cradia/Qwen3.8-2.4T-A95B | |
Qwen3.8-27B huggingface/litert-community-qwen3.8-27b · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/litert-community/Qwen3.8-27B | |
Qwen3.8-27B-GGUF huggingface/42ailab-qwen3.8-27b-gguf · Qwen tool_calling · structured_output · vision | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/42ailab/Qwen3.8-27B-GGUF | |
Qwen3.8-27B-Hermes-oQ4 huggingface/onyxailabs-qwen3.8-27b-hermes-oq4 · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/OnyxAILabs/Qwen3.8-27B-Hermes-oQ4 | |
Qwen3.8-27B-NVG-0.55bpw-Experimental-cmf huggingface/infosave-qwen3.8-27b-nvg-0.55bpw-experimental-cmf · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/infosave/Qwen3.8-27B-NVG-0.55bpw-Experimental-cmf | |
Qwen3.8-27B-pi-adapted-oQ6-bf16-mtp-dflash2-kapitsa huggingface/jongstra-qwen3.8-27b-pi-adapted-oq6-bf16-mtp-dflash2-kapitsa · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/jongstra/Qwen3.8-27B-pi-adapted-oQ6-bf16-mtp-dflash2-kapitsa | |
Qwen3.8-27B-trellis-2.8bpw-abliterated-ignis huggingface/gpillon-qwen3.8-27b-trellis-2.8bpw-abliterated-ignis · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/gpillon/Qwen3.8-27B-trellis-2.8bpw-abliterated-ignis | |
Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4 huggingface/esatapedico-qwen3.8-27b-ultimate-heretic-uncensored-turbo-brilliance-50x-agi-neo-nvfp4 · Qwen tool_calling · structured_output · vision | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4 | |
Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4-MTP-GGUF huggingface/esatapedico-qwen3.8-27b-ultimate-heretic-uncensored-turbo-brilliance-50x-agi-neo-nvfp4-mtp-gguf · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4-MTP-GGUF | |
Qwen3.8-27B-XeFP4 huggingface/kinoq-qwen3.8-27b-xefp4 · Qwen tool_calling · structured_output | local 24GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/KINOQ/Qwen3.8-27B-XeFP4 | |
qwen3.8-cyber-uncensored huggingface/timdedid-qwen3.8-cyber-uncensored · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/timdedid/qwen3.8-cyber-uncensored | |
Qwen3.8-Flash-Next-3.55BPW-MTP huggingface/beling86-qwen3.8-flash-next-3.55bpw-mtp · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/Beling86/Qwen3.8-Flash-Next-3.55BPW-MTP | |
Qwen3.8-Flash-Next-T3a392-Ampere-SM80-46GiB-GPU-Weights huggingface/sachk0-qwen3.8-flash-next-t3a392-ampere-sm80-46gib-gpu-weights · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/sachk0/Qwen3.8-Flash-Next-T3a392-Ampere-SM80-46GiB-GPU-Weights | |
Qwen3.8-Flash-Next-TR2.31-G-GGUF huggingface/ternii-qwen3.8-flash-next-tr2.31-g-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Ternii/Qwen3.8-Flash-Next-TR2.31-G-GGUF | |
Qwen4 Max qwen/qwen4-max · Qwen reasoning · vision · tool_calling · structured_output · long_context | both 8GB+ RAM | 1M | $1.43 / $4.28 | provider reported · 2026-11-16 https://openrouter.ai/models | |
QwenPU-RF huggingface/pratx1-qwenpu-rf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/pratx1/QwenPU-RF | |
redline-bank-qwen3-0.6b huggingface/ahmedoussama-redline-bank-qwen3-0.6b · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/ahmedoussama/redline-bank-qwen3-0.6b | |
Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step760 huggingface/thkim0305-snu-safety_tuning-qwen3.5-4b-base-grpo-mixture8-binary-lr1e-6-kl0.001-p15-k8-step760 · Qwen tool_calling · structured_output · reasoning · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step760 | |
Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step787 huggingface/thkim0305-snu-safety_tuning-qwen3.5-4b-base-grpo-mixture8-binary-lr1e-6-kl0.001-p15-k8-step787 · Qwen tool_calling · structured_output · reasoning · vision | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step787 | |
SFT-Qwen3-0.6B-ALFWorld huggingface/tommmxsx-sft-qwen3-0.6b-alfworld · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/tommmxsx/SFT-Qwen3-0.6B-ALFWorld | |
sixthphysics-qwen3.5-9b-GGUF huggingface/d4ydy-sixthphysics-qwen3.5-9b-gguf · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/d4ydy/sixthphysics-qwen3.5-9b-GGUF | |
smart-home-energy-qwen3-scratch huggingface/design-thinking-slm-smart-home-energy-qwen3-scratch · Qwen tool_calling · structured_output · reasoning | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Design-Thinking-SLM/smart-home-energy-qwen3-scratch | |
tech-challenge-gemma-llm-fine-tuning-light huggingface/ramoncg-tech-challenge-gemma-llm-fine-tuning-light · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/ramoncg/tech-challenge-gemma-llm-fine-tuning-light | |
tech-challenge-gemma-llm-fine-tuning-light-v6 huggingface/ramoncg-tech-challenge-gemma-llm-fine-tuning-light-v6 · Google Gemini tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/ramoncg/tech-challenge-gemma-llm-fine-tuning-light-v6 | |
Tenet-8B-Qwen3-Unslop-v2 huggingface/mr-andrey-isachenko-tenet-8b-qwen3-unslop-v2 · Qwen tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-20 https://huggingface.co/mr-andrey-isachenko/Tenet-8B-Qwen3-Unslop-v2 | |
test-save-tiny-random-llama3-smashed-pro huggingface/pruna-test-test-save-tiny-random-llama3-smashed-pro · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/pruna-test/test-save-tiny-random-llama3-smashed-pro | |
Text Embedding 3 Large text-embedding-3-large · OpenAI embedding | cloud Direct API | 8k | $0.13 / $0.00 | verified · 2026-11-12 https://openai.com/api/pricing/ | |
ultron-qwen25-05b-onnx-web huggingface/mosabbir125-ultron-qwen25-05b-onnx-web · Qwen tool_calling · structured_output · reasoning | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/Mosabbir125/ultron-qwen25-05b-onnx-web | |
voxtral-mini-3b-text-llama huggingface/vxltxrllc-voxtral-mini-3b-text-llama · Meta / Llama tool_calling · structured_output | local 8GB+ RAM | 131k | $0.00 / $0.00 | community reported · 2026-11-21 https://huggingface.co/vxltxrllc/voxtral-mini-3b-text-llama |
So sánh Model tiêu biểu
Lập trình chủ lực & Gọi công cụ
So sánh Claude Sonnet 4.5 và GPT-4.1: Lập trình, Ngữ cảnh & Chi phí
Kiến trúc Ngữ cảnh dài & Đa phương thức
So sánh Gemini 2.5 Pro và Claude Sonnet 4.5: Ngữ cảnh dài & Đa phương thức
Suy luận chuyên sâu & Gỡ lỗi
So sánh DeepSeek R1 và OpenAI o3: Chi phí suy luận & Đánh đổi
Tự động hóa tiết kiệm & Tác vụ tần suất cao
So sánh GPT-4.1 mini và Gemini 2.5 Flash: Cấu hình Tiết kiệm
Mô hình mã nguồn mở cục bộ & Yêu cầu phần cứng
So sánh Qwen 2.5 Coder 32B (Ollama) và Llama 3.3 70B: Phần cứng cục bộ & Quyền riêng tư
Kỹ thuật đám mây tiết kiệm so với Chuyên gia lập trình
So sánh DeepSeek V3 và Mistral Codestral 25.01: Giá, Lập trình & Ngữ cảnh