Free Models
免费模型
以下模型在对应平台提供免费额度或免费调用。各平台的免费政策（速率限制、每日额度、是否限免）以官方说明为准。
共 325 个免费模型，按发布日期排序
| 模型 | 机构 | 发布日期 | 上下文 | 免费可用平台 |
|---|---|---|---|---|
| Laguna S 2.1 Free | — | 2026-07-21 | 1.0M | OpenCode Zen OpenRouter Poolside Vercel AI Gateway |
| Qwen3.8 Max Preview | Alibaba Cloud / Qwen Team | 2026-07-19 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) |
| Kimi K3 | Moonshot AI | 2026-07-16 | 1.0M | Kenari Kimi For Coding ZenMux |
| Agentic Chat (GPT-5.6 Sol) | — | 2026-07-09 | 922K | GitLab Duo |
| Agentic Chat (GPT-5.6 Terra) | — | 2026-07-09 | 922K | GitLab Duo |
| Agentic Chat (GPT-5.6 Luna) | — | 2026-07-09 | 922K | GitLab Duo |
| GPT-5.6 Luna | — | 2026-07-09 | 1.1M | Kenari |
| GPT-5.6 Sol | — | 2026-07-09 | 1.1M | Kenari |
| GPT-5.6 Terra | — | 2026-07-09 | 1.1M | Kenari |
| Grok 4.5 | — | 2026-07-08 | 500K | Kenari |
| Hy3 | Tencent | 2026-07-06 | 256K | OpenCode Zen Tencent Token Plan Tencent TokenHub |
| Laguna XS 2.1 (free) | — | 2026-07-02 | 262K | OpenRouter Poolside |
| Agentic Chat (Claude Sonnet 5) | — | 2026-06-30 | 1.0M | GitLab Duo |
| Claude Sonnet 5 | Anthropic | 2026-06-30 | 1.0M | Kenari ZenMux |
| North Mini Code | Cohere | 2026-06-17 | 256K | Cohere OpenCode Zen OpenRouter |
| GLM-5.2 | Zhipu AI | 2026-06-13 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) Kenari Nvidia Umans AI Coding Plan UnoRouter Z.AI Coding Plan ZenMux Zhipu AI Coding Plan |
| Kimi K2.7 Code | Moonshot AI | 2026-06-12 | 262K | Alibaba Token Plan Alibaba Token Plan (China) Kenari Kimi For Coding Umans AI Coding Plan ZenMux |
| Kimi For Coding HighSpeed | — | 2026-06-12 | 262K | Kimi For Coding |
| Umans Coder | — | 2026-06-12 | 262K | Umans AI Coding Plan |
| Agentic Chat (Claude Fable 5) | — | 2026-06-09 | 1.0M | GitLab Duo |
| Claude Fable 5 | Anthropic | 2026-06-09 | 1.0M | Kenari |
| Trendyol 7B | — | 2026-06-06 | 33K | LLMTR |
| Magibu 11B v8 | — | 2026-06-05 | 8K | LLMTR |
| Nemotron 3 Ultra 550B A55B | NVIDIA | 2026-06-04 | 1.0M | Kenari UnoRouter |
| Nemotron 3 Ultra Free | — | 2026-06-04 | 1.0M | OpenCode Zen OpenRouter |
| Nemotron 3.5 Content Safety (free) | — | 2026-06-04 | 128K | OpenRouter |
| Qwen3.7 Plus | Alibaba Cloud / Qwen Team | 2026-06-02 | 1.0M | Alibaba Coding Plan Alibaba Coding Plan (China) Alibaba Token Plan Alibaba Token Plan (China) Kenari |
| MiniMax-M3 | MiniMax | 2026-06-01 | 1.0M | Kenari MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) Nvidia OpenCode Zen |
| Wan2.7 Image Pro | Alibaba Cloud / Qwen Team | 2026-05-29 | 8K | Alibaba Token Plan Alibaba Token Plan (China) |
| Wan2.7 Image | Alibaba Cloud / Qwen Team | 2026-05-29 | 8K | Alibaba Token Plan Alibaba Token Plan (China) |
| Step 3.7 Flash | — | 2026-05-29 | 256K | Nvidia UnoRouter ZenMux |
| Agentic Chat (Claude Opus 4.8) | — | 2026-05-28 | 1.0M | GitLab Duo |
| Claude Opus 4.8 | Anthropic | 2026-05-28 | 1.0M | Kenari |
| Qwen3.7 Max | Alibaba Cloud / Qwen Team | 2026-05-21 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) |
| Ring 2.6 1T Free | — | 2026-05-08 | 262K | OpenCode Zen |
| Gemini 3.1 Flash Lite | — | 2026-05-07 | 1.0M | Kenari |
| Baidu: CoBuddy (free) | — | 2026-05-06 | 131K | Kilo Gateway |
| Sincap | — | 2026-05-05 | 128K | LLMTR |
| NVIDIA: Nemotron 3 Nano Omni (free) | — | 2026-04-28 | 256K | Kilo Gateway |
| Owl Alpha | — | 2026-04-28 | 1.0M | Kilo Gateway |
| Poolside: Laguna XS.2 (free) | — | 2026-04-28 | 262K | Kilo Gateway |
| Poolside: Laguna M.1 (free) | — | 2026-04-28 | 262K | Kilo Gateway |
| Nemotron 3 Nano Omni | — | 2026-04-28 | 256K | Nvidia OpenRouter |
| Laguna M.1 (free) | — | 2026-04-28 | 262K | OpenRouter Poolside |
| Qwen3.6 Flash | Alibaba Cloud / Qwen Team | 2026-04-27 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) |
| DeepSeek V4 Flash | DeepSeek | 2026-04-24 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) Kenari OpenCode Zen UnoRouter |
| DeepSeek V4 Pro | DeepSeek | 2026-04-24 | 1.0M | Alibaba Token Plan Alibaba Token Plan (China) Kenari UnoRouter |
| MiMo-V2.5 | Xiaomi | 2026-04-24 | 1.0M | Kenari OpenCode Zen Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| Agentic Chat (GPT-5.5) | — | 2026-04-23 | 922K | GitLab Duo |
| GPT-5.5 | — | 2026-04-23 | 922K | Kenari UnoRouter |
| Xiaomi MiMo-V2.5-Pro (free) | — | 2026-04-22 | 1.0M | AIHubMix |
| Xiaomi MiMo-V2.5 (free) | — | 2026-04-22 | 1.0M | AIHubMix |
| Qwen3.6 27B FP8 | — | 2026-04-22 | 262K | InferX |
| MiMo-V2.5-Pro | Xiaomi | 2026-04-22 | 1.0M | Kenari Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| MiMo-V2.5-TTS-VoiceClone | — | 2026-04-22 | 8K | Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| MiMo-V2.5-TTS | — | 2026-04-22 | 8K | Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| MiMo-V2.5-TTS-VoiceDesign | — | 2026-04-22 | 8K | Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| Kimi K2.6 | Moonshot AI | 2026-04-21 | 262K | Alibaba Token Plan Alibaba Token Plan (China) Kenari Nvidia Privatemode AI |
| GPT-Image-2 | OpenAI | 2026-04-21 | 272K | Kenari |
| Pareto Code Router | — | 2026-04-21 | 200K | Kilo Gateway |
| Ling 2.6 Flash Free | — | 2026-04-21 | 262K | OpenCode Zen |
| Hy3 preview | Tencent | 2026-04-20 | 256K | OpenCode Zen Tencent TokenHub |
| Qwen3.6 35B A3B FP8 | — | 2026-04-17 | 262K | InferX |
| Umans Flash | — | 2026-04-17 | 262K | Umans AI Coding Plan |
| Qwen3.6 35B A3B | — | 2026-04-17 | 262K | Umans AI Coding Plan |
| Agentic Chat (Claude Opus 4.7) | — | 2026-04-16 | 1.0M | GitLab Duo |
| Grok Build 0.1 | — | 2026-04-16 | 256K | Kenari |
| Claude Opus 4.7 | Anthropic | 2026-04-16 | 1.0M | Kenari |
| nemotron-3-content-safety | — | 2026-04-16 | 128K | Nvidia |
| synthetic-video-detector | — | 2026-04-16 | — | Nvidia |
| Active Speaker Detection | — | 2026-04-16 | — | Nvidia |
| Z-Code | — | 2026-04-15 | 1.0M | Zeldoc |
| Coding GLM 5.1 (free) | — | 2026-04-11 | 200K | AIHubMix |
| GLM-5.1 | Zhipu AI | 2026-04-07 | 205K | Alibaba Token Plan Alibaba Token Plan (China) Kenari Umans AI Coding Plan Z.AI Coding Plan Zhipu AI Coding Plan |
| Qwen3.6 Plus | Alibaba Cloud / Qwen Team | 2026-04-02 | 1.0M | Alibaba Coding Plan Alibaba Coding Plan (China) Alibaba Token Plan Alibaba Token Plan (China) OpenCode Zen |
| Gemma 4 E4B Instruct (MLX 4-bit) | — | 2026-04-02 | 33K | Atomic Chat |
| Gemma 4 E4B Instruct (IQ4_XS) | — | 2026-04-02 | 33K | Atomic Chat |
| Gemma 4 31B IT FP8 | — | 2026-04-02 | 262K | InferX |
| Gemma 4 31B IT | 2026-04-02 | 262K | Kenari Nvidia UnoRouter | |
| Gemma 4 31B (free) | — | 2026-04-02 | 262K | OpenRouter Poe |
| Gemma 4 26B A4B (free) | — | 2026-04-02 | 262K | OpenRouter |
| GLM-5V-Turbo | Zhipu AI | 2026-04-01 | 200K | Z.AI Coding Plan Zhipu AI Coding Plan |
| llama-nemotron-rerank-vl-1b-v2 | — | 2026-03-31 | 128K | Nvidia |
| Google: Lyria 3 Pro Preview | — | 2026-03-30 | 1.0M | Kilo Gateway |
| Google: Lyria 3 Clip Preview | — | 2026-03-30 | 1.0M | Kilo Gateway |
| Qwen3.5 Omni Plus | — | 2026-03-30 | 984K | NanoGPT |
| Qwen3.5 Omni Flash | — | 2026-03-30 | 49K | NanoGPT |
| Lyria 3 Pro Preview | — | 2026-03-30 | 1.0M | OpenRouter |
| Lyria 3 Clip Preview | — | 2026-03-30 | 1.0M | OpenRouter |
| Coding MiniMax M2.7 (Free) | — | 2026-03-18 | 205K | AIHubMix |
| MiniMax-M2.7 | MiniMax | 2026-03-18 | 205K | MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) Nvidia UnoRouter |
| MiniMax-M2.7-highspeed | MiniMax | 2026-03-18 | 205K | MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) |
| MiMo-V2-Pro | Xiaomi | 2026-03-18 | 1.0M | OpenCode Zen Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| MiMo V2 Omni Free | — | 2026-03-18 | 262K | OpenCode Zen |
| MiMo-V2-TTS | — | 2026-03-18 | 8K | Xiaomi Token Plan (China) Xiaomi Token Plan (Europe) Xiaomi Token Plan (Singapore) |
| Agentic Chat (GPT-5.4 Mini) | — | 2026-03-17 | 272K | GitLab Duo |
| Agentic Chat (GPT-5.4 Nano) | — | 2026-03-17 | 272K | GitLab Duo |
| GPT-5.4 mini | — | 2026-03-17 | 272K | Kenari |
| nemotron-voicechat | — | 2026-03-16 | 128K | Nvidia |
| mistral-small-4-119b-2603 | — | 2026-03-16 | 128K | Nvidia |
| GLM-5-Turbo | Zhipu AI | 2026-03-16 | 200K | Z.AI Coding Plan Zhipu AI Coding Plan |
| Kilo Auto Free | — | 2026-03-15 | 205K | Kilo Gateway |
| Body Builder (beta) | — | 2026-03-15 | 128K | Kilo Gateway |
| Auto Router | — | 2026-03-15 | 2.0M | Kilo Gateway |
| NVIDIA: Nemotron 3 Super (free) | — | 2026-03-12 | 262K | Kilo Gateway |
| Nemotron 3 Super 120B A12B | NVIDIA | 2026-03-11 | 262K | Kenari |
| Nemotron 3 Super Free | — | 2026-03-11 | 262K | OpenCode Zen OpenRouter |
| Auto | — | 2026-03-08 | 131K | Tencent Coding Plan (China) |
| Tencent HY 2.0 Instruct | — | 2026-03-08 | 131K | Tencent Coding Plan (China) |
| Tencent HY 2.0 Think | — | 2026-03-08 | 131K | Tencent Coding Plan (China) |
| Hunyuan-T1 | — | 2026-03-08 | 131K | Tencent Coding Plan (China) |
| Hunyuan-TurboS | — | 2026-03-08 | 131K | Tencent Coding Plan (China) |
| Qwen 3.5 9B (Q4_K_M) | — | 2026-03-05 | 33K | Atomic Chat |
| Qwen 3.5 9B (MLX 4-bit) | — | 2026-03-05 | 33K | Atomic Chat |
| Agentic Chat (GPT-5.4) | — | 2026-03-05 | 922K | GitLab Duo |
| GPT-5.4 | — | 2026-03-05 | 922K | UnoRouter |
| GPT-5.3-Codex-Spark | — | 2026-03-04 | 128K | Poe |
| Qwen Image 2.0 Pro | — | 2026-03-03 | 8K | Alibaba Token Plan Alibaba Token Plan (China) |
| Qwen Image 2.0 | — | 2026-03-03 | 8K | Alibaba Token Plan Alibaba Token Plan (China) |
| gliner-pii | — | 2026-03-03 | 128K | Nvidia |
| Qwen/Qwen3.5-4B | — | 2026-03-03 | 262K | SiliconFlow (China) |
| cosmos-transfer2.5-2b | — | 2026-02-26 | — | Nvidia |
| Qwen3.5 122B A10B NVFP4 | — | 2026-02-23 | 256K | InferX |
| Qwen3.5 122B-A10B | — | 2026-02-23 | 262K | Nvidia |
| Agentic Chat (Claude Sonnet 4.6) | — | 2026-02-17 | 1.0M | GitLab Duo |
| Qwen3.5 Plus | Alibaba Cloud / Qwen Team | 2026-02-16 | 1.0M | Alibaba Coding Plan Alibaba Coding Plan (China) |
| Qwen3.5-397B-A17B | — | 2026-02-16 | 262K | Nvidia UnoRouter |
| MiniMax-M2.5-highspeed | MiniMax | 2026-02-13 | 205K | MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) |
| MiniMax-M2.5 | MiniMax | 2026-02-12 | 205K | Alibaba Coding Plan Alibaba Coding Plan (China) Alibaba Token Plan Alibaba Token Plan (China) MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) OpenCode Zen Tencent Coding Plan (China) |
| GLM-5 | Zhipu AI | 2026-02-12 | 205K | Alibaba Coding Plan Alibaba Coding Plan (China) Alibaba Token Plan Alibaba Token Plan (China) OpenCode Zen Tencent Coding Plan (China) |
| llama-nemotron-embed-vl-1b-v2 | — | 2026-02-10 | 33K | Nvidia |
| Agentic Chat (GPT-5.3 Codex) | — | 2026-02-05 | 272K | GitLab Duo |
| Agentic Chat (Claude Opus 4.6) | — | 2026-02-05 | 1.0M | GitLab Duo |
| Qwen3 Coder Next | — | 2026-02-03 | 262K | Alibaba Coding Plan Alibaba Coding Plan (China) |
| Qwen3 Coder Next FP8 | — | 2026-02-03 | 256K | InferX |
| Qwen3 Coder Next FP8 1M | — | 2026-02-03 | 1.0M | InferX |
| Step 3.5 Flash | — | 2026-02-02 | 256K | Nvidia |
| Free Models Router | — | 2026-02-01 | 200K | Kilo Gateway OpenRouter |
| PaddlePaddle/PaddleOCR-VL-1.5 | — | 2026-01-29 | 16K | SiliconFlow (China) |
| Trinity Large Preview | — | 2026-01-28 | 131K | OpenCode Zen |
| Kimi K2.5 | Moonshot AI | 2026-01-27 | 262K | Alibaba Coding Plan Alibaba Coding Plan (China) Alibaba Token Plan Alibaba Token Plan (China) OpenCode Zen Tencent Coding Plan (China) |
| Kimi-K2.5-FW | — | 2026-01-27 | 246K | Poe |
| Qwen3-Max | Alibaba Cloud / Qwen Team | 2026-01-23 | 262K | Alibaba Coding Plan Alibaba Coding Plan (China) iFlow |
| Agentic Chat (GPT-5.2) | — | 2026-01-23 | 272K | GitLab Duo |
| Agentic Chat (GPT-5 Mini) | — | 2026-01-22 | 272K | GitLab Duo |
| Agentic Chat (GPT-5.2 Codex) | — | 2026-01-22 | 272K | GitLab Duo |
| Agentic Chat (GPT-5 Codex) | — | 2026-01-22 | 272K | GitLab Duo |
| Agentic Chat (GPT-5.1) | — | 2026-01-22 | 272K | GitLab Duo |
| nemotron-content-safety-reasoning-4b | — | 2026-01-22 | 128K | Nvidia |
| GLM-4.7-Flash | Zhipu AI | 2026-01-19 | 200K | EmpirioLabs AI Hugging Face Kenari Z.AI ZenMux Zhipu AI |
| FLUX.2 Klein 4B | — | 2026-01-14 | 41K | Nvidia |
| Agentic Chat (Claude Haiku 4.5) | — | 2026-01-08 | 200K | GitLab Duo |
| Agentic Chat (Claude Sonnet 4.5) | — | 2026-01-08 | 200K | GitLab Duo |
| Agentic Chat (Claude Opus 4.5) | — | 2026-01-08 | 200K | GitLab Duo |
| usdcode | — | 2026-01-01 | 128K | Nvidia |
| XiaomiMiMo/MiMo-V2-Flash | — | 2026-01 | 262K | Jiekou.AI OpenCode Zen |
| MiniMax-M2.1 | MiniMax | 2025-12-23 | 205K | MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) OpenCode Zen |
| GLM-4.7 | Zhipu AI | 2025-12-22 | 205K | Alibaba Coding Plan Alibaba Coding Plan (China) KUAE Cloud Coding Plan OpenCode Zen Z.AI Coding Plan Zhipu AI Coding Plan |
| Nemotron 3 Nano 30B A3B | NVIDIA | 2025-12-15 | 262K | Kenari Nvidia OpenRouter |
| riva-translate-4b-instruct-v1_1 | — | 2025-12-12 | 128K | Nvidia |
| Devstral 2 2512 | Mistral AI | 2025-12-09 | 262K | Cortecs |
| Devstral Small 2 | — | 2025-12-09 | 256K | Mistral |
| GLM 4.6V Flash (Free) | — | 2025-12-08 | 200K | ZenMux |
| DeepSeek V3.2 | — | 2025-12-03 | 131K | Alibaba Token Plan Alibaba Token Plan (China) |
| Lynkr Auto (complexity routing) | — | 2025-12-03 | 128K | Lynkr |
| Nova 2 Pro | — | 2025-12-03 | 1.0M | Nova |
| Mistral Large 3 675B Instruct 2512 | — | 2025-12-02 | 262K | Nvidia |
| Nova 2 Lite | — | 2025-12-01 | 1.0M | Nova |
| Deepgram Aura 2 (ES) | — | 2025-11-14 | 128K | Cloudflare AI Gateway |
| Deepgram Nova 3 | — | 2025-11-14 | 128K | Cloudflare AI Gateway |
| Deepgram Aura 2 (EN) | — | 2025-11-14 | 128K | Cloudflare AI Gateway |
| MyShell MeloTTS | — | 2025-11-14 | 128K | Cloudflare AI Gateway |
| Pipecat Smart Turn v2 | — | 2025-11-14 | 128K | Cloudflare AI Gateway |
| streampetr | — | 2025-11-13 | 128K | Nvidia |
| llama-3.1-nemotron-safety-guard-8b-v3 | — | 2025-10-28 | 128K | Nvidia |
| Nemotron Nano 12B 2 VL (free) | — | 2025-10-28 | 128K | OpenRouter |
| MiniMax-M2 | MiniMax | 2025-10-27 | 197K | MiniMax Token Plan (minimax.io) MiniMax Token Plan (minimaxi.com) |
| deepseek-ai/DeepSeek-OCR | — | 2025-10-20 | 8K | SiliconFlow (China) |
| Big Pickle | — | 2025-10-17 | 160K | OpenCode Zen |
| Claude Haiku 4.5 (latest) | — | 2025-10-15 | 200K | LLM Gateway |
| GLM-4.6 | Zhipu AI | 2025-09-30 | 203K | ModelScope iFlow |
| Mistral Medium 3 | — | 2025-09-25 | 131K | EmpirioLabs AI Nvidia |
| Magistral Small 2506 | — | 2025-09-25 | 33K | Nvidia |
| Kimi-K2-0905 | Moonshot AI | 2025-09-05 | 262K | Nvidia iFlow |
| ByteDance-Seed/Seed-OSS-36B-Instruct | — | 2025-09-04 | 262K | Nvidia |
| Grok Code Fast 1 | — | 2025-08-20 | 256K | OpenCode Zen |
| Qwen Image Edit | — | 2025-08-19 | — | Nvidia |
| nvidia-nemotron-nano-9b-v2 | — | 2025-08-18 | 131K | Nvidia |
| Nemotron Nano 9B V2 (free) | — | 2025-08-18 | 128K | OpenRouter |
| FLUX.1-Kontext-dev | — | 2025-08-12 | 41K | Nvidia |
| Qwen Image | — | 2025-08-07 | — | Nvidia |
| GPT Oss 120b | OpenAI | 2025-08-05 | 131K | Cortecs Kenari Nvidia Privatemode AI |
| GPT OSS 20B | OpenAI | 2025-08-05 | 131K | Kenari LMStudio Nvidia OpenRouter |
| Qwen3 Coder 30B A3B Instruct | — | 2025-07-31 | 262K | ModelScope |
| Qwen3 30B A3B 2507 | — | 2025-07-30 | 262K | LMStudio |
| Qwen3 30B A3B Thinking 2507 | — | 2025-07-30 | 262K | ModelScope |
| Qwen3 30B A3B Instruct 2507 | — | 2025-07-30 | 262K | ModelScope |
| GLM-4.5-Flash | Zhipu AI | 2025-07-28 | 200K | EmpirioLabs AI UnoRouter Z.AI Zhipu AI |
| GLM-4.5 | — | 2025-07-28 | 131K | ModelScope |
| GLM-4.5-Air | Zhipu AI | 2025-07-28 | 131K | Z.AI Coding Plan Zhipu AI Coding Plan |
| Phi 4 Multimodal | — | 2025-07-26 | 128K | Nvidia |
| Qwen3-235B-A22B-Thinking-2507 | — | 2025-07-25 | 262K | ModelScope |
| sarvam-m | — | 2025-07-25 | 128K | Nvidia |
| llama-3_2-nemoretriever-300m-embed-v1 | — | 2025-07-24 | 33K | Nvidia |
| Qwen3 Coder Plus | Alibaba Cloud / Qwen Team | 2025-07-23 | 1.0M | Alibaba Coding Plan Alibaba Coding Plan (China) iFlow |
| Qwen3 Coder 30B | — | 2025-07-23 | 262K | LMStudio |
| Qwen3 Coder 480B A35B Instruct | — | 2025-07-23 | 262K | Nvidia |
| Qwen3-235B-A22B-Thinking | Alibaba Cloud / Qwen Team | 2025-07-01 | 256K | iFlow |
| Qwen3-235B-A22B-Instruct | — | 2025-07-01 | 256K | iFlow |
| Voxtral Mini 3B | — | 2025-07 | 32K | Privatemode AI |
| Mistral Small 3.2 24B Instruct | — | 2025-06-20 | 33K | Meganova |
| Gemini 2.5 Flash | — | 2025-06-17 | 1.0M | Kenari |
| Gemini 2.5 Flash-Lite | — | 2025-06-17 | 1.0M | Kenari |
| cosmos-transfer1-7b | — | 2025-06-13 | — | Nvidia |
| Gemma 3n E2b It | — | 2025-06-12 | 128K | Nvidia |
| mistral-nemotron | — | 2025-06-11 | 128K | Nvidia |
| Qwen3-Embedding 4B | — | 2025-06-06 | 32K | Privatemode AI |
| Gemma 3n E4b It | — | 2025-06-03 | 128K | Nvidia |
| DeepSeek-R1-0528 | — | 2025-05-28 | 66K | GitHub Models |
| magpie-tts-zeroshot | — | 2025-05-22 | — | Nvidia |
| Mistral Medium 3 (25.05) | — | 2025-05-01 | 128K | GitHub Models |
| Qwen3 235B A22B Instruct 2507 | — | 2025-04-28 | 262K | ModelScope |
| GPT-4.1-mini | — | 2025-04-14 | 128K | GitHub Models |
| GPT-4.1 | — | 2025-04-14 | 128K | GitHub Models |
| GPT-4.1-nano | — | 2025-04-14 | 128K | GitHub Models |
| BART Large CNN | — | 2025-04-09 | 128K | Cloudflare AI Gateway |
| Llama 4 Maverick 17B 128E Instruct FP8 | — | 2025-04-05 | 128K | GitHub Models Llama Vercel AI Gateway |
| Cerebras-Llama-4-Scout-17B-16E-Instruct | — | 2025-04-05 | 128K | Llama |
| Cerebras-Llama-4-Maverick-17B-128E-Instruct | — | 2025-04-05 | 128K | Llama |
| Groq-Llama-4-Maverick-17B-128E-Instruct | — | 2025-04-05 | 128K | Llama |
| Llama-4-Scout-17B-16E-Instruct-FP8 | — | 2025-04-05 | 128K | Llama Vercel AI Gateway |
| Llama Guard 4 12B | — | 2025-04-05 | 128K | Nvidia |
| Llama 4 Maverick 17b 128e Instruct | — | 2025-04-01 | 128K | Nvidia |
| Mistral-7B-Instruct-v0.3 | — | 2025-04-01 | 66K | Nvidia |
| DeepSeek-V3-0324 | — | 2025-03-24 | 128K | GitHub Models |
| bevformer | — | 2025-03-18 | 128K | Nvidia |
| cosmos-predict1-5b | — | 2025-03-18 | — | Nvidia |
| sparsedrive | — | 2025-03-18 | 128K | Nvidia |
| nv-embedcode-7b-v1 | — | 2025-03-17 | 33K | Nvidia |
| Mistral Small 3.1 | — | 2025-03-01 | 128K | GitHub Models |
| Llama 4 Scout 17B 16E Instruct | — | 2025-01-31 | 128K | GitHub Models |
| OpenAI o3 | — | 2025-01-31 | 200K | GitHub Models |
| OpenAI o3-mini | — | 2025-01-31 | 200K | GitHub Models |
| OpenAI o4-mini | — | 2025-01-31 | 200K | GitHub Models |
| MAI-DS-R1 | — | 2025-01-20 | 66K | GitHub Models |
| DeepSeek-R1 | DeepSeek | 2025-01-20 | 128K | GitHub Models iFlow |
| DeepSeek R1 Distill Qwen 1.5B | — | 2025-01-01 | 33K | Alibaba (China) |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 2025-01-01 | 33K | Alibaba (China) |
| Codestral 25.01 | — | 2025-01-01 | 32K | GitHub Models |
| DeepSeek-V3.2-Exp | — | 2025-01-01 | 128K | iFlow |
| Qwen3-VL-Plus | Alibaba Cloud / Qwen Team | 2025-01-01 | 256K | iFlow |
| Qwen3-Max-Preview | — | 2025-01-01 | 256K | iFlow |
| Llama 3.1 8B Instruct | — | 2025-01-01 | 16K | Nvidia |
| OrcaRouter Auto | — | 2025-01-01 | 128K | OrcaRouter |
| DeepSeek-V3 | DeepSeek | 2024-12-26 | 128K | iFlow |
| Phi-4-mini-instruct | — | 2024-12-11 | 128K | GitHub Models |
| Phi-4 | — | 2024-12-11 | 16K | GitHub Models |
| Phi-4-Reasoning | — | 2024-12-11 | 128K | GitHub Models |
| Phi-4-multimodal-instruct | — | 2024-12-11 | 128K | GitHub Models |
| Phi-4-mini-reasoning | — | 2024-12-11 | 128K | GitHub Models |
| Grok 3 Mini | — | 2024-12-09 | 128K | GitHub Models |
| Grok 3 | — | 2024-12-09 | 128K | GitHub Models |
| Llama-3.3-70B-Instruct | Meta | 2024-12-06 | 128K | GitHub Models Llama Nvidia Vercel AI Gateway |
| Llama-3.3-8B-Instruct | — | 2024-12-06 | 128K | Llama |
| Qwen3-32B | Alibaba Cloud / Qwen Team | 2024-12-01 | 128K | iFlow |
| Kimi-K2 | — | 2024-12-01 | 128K | iFlow |
| Qwen3-235B-A22B | — | 2024-12-01 | 128K | iFlow |
| Phi-4-Mini | — | 2024-12-01 | 131K | Nvidia |
| Qwen3-Next-80B-A3B-Instruct | — | 2024-12-01 | 262K | Nvidia |
| Qwen2.5 Coder 32b Instruct | — | 2024-11-06 | 128K | Nvidia |
| Mistral Large 24.11 | — | 2024-11-01 | 128K | GitHub Models |
| Cohere Command A | — | 2024-11-01 | 128K | GitHub Models |
| Ministral 3B | — | 2024-10-22 | 128K | GitHub Models |
| studiovoice | — | 2024-10-03 | 128K | Nvidia |
| Llama-3.2-11B-Vision-Instruct | — | 2024-09-25 | 128K | GitHub Models Nvidia |
| Llama-3.2-90B-Vision-Instruct | — | 2024-09-25 | 128K | GitHub Models Nvidia |
| Llama 3.2 1b Instruct | — | 2024-09-18 | 128K | Nvidia |
| Llama 3.2 3B Instruct | — | 2024-09-18 | 33K | Nvidia |
| OpenAI o1-mini | — | 2024-09-12 | 128K | GitHub Models |
| OpenAI o1 | — | 2024-09-12 | 200K | GitHub Models |
| OpenAI o1-preview | — | 2024-09-12 | 128K | GitHub Models |
| dracarys-llama-3.1-70b-instruct | — | 2024-09-11 | 128K | Nvidia |
| AI21 Jamba 1.5 Large | — | 2024-08-29 | 256K | GitHub Models |
| AI21 Jamba 1.5 Mini | — | 2024-08-29 | 256K | GitHub Models |
| esm2-650m | — | 2024-08-29 | 128K | Nvidia |
| nemotron-mini-4b-instruct | — | 2024-08-21 | 128K | Nvidia |
| Phi-3.5-vision instruct (128k) | — | 2024-08-20 | 128K | GitHub Models |
| Phi-3.5-mini instruct (128k) | — | 2024-08-20 | 128K | GitHub Models |
| Phi-3.5-MoE instruct (128k) | — | 2024-08-20 | 128K | GitHub Models |
| Cohere Command R 08-2024 | — | 2024-08-01 | 128K | GitHub Models |
| FLUX.1-dev | — | 2024-08-01 | 4K | Nvidia |
| FLUX.1-schnell | — | 2024-08-01 | 77 | Nvidia |
| usdvalidate | — | 2024-07-24 | — | Nvidia |
| Meta Llama 3.1 8B Instruct (GGUF) | — | 2024-07-23 | 131K | Atomic Chat |
| Llama 3.1 405B Instruct | Meta | 2024-07-23 | 128K | Cortecs |
| Meta-Llama-3.1-8B-Instruct | — | 2024-07-23 | 128K | GitHub Models |
| Meta-Llama-3.1-405B-Instruct | — | 2024-07-23 | 128K | GitHub Models |
| Meta-Llama-3.1-70B-Instruct | — | 2024-07-23 | 128K | GitHub Models |
| Mistral Nemo | — | 2024-07-18 | 128K | GitHub Models |
| GPT-4o mini | — | 2024-07-18 | 128K | GitHub Models |
| Llama 3.1 70b Instruct | — | 2024-07-16 | 128K | Nvidia |
| Gemma 2 2b It | — | 2024-07-16 | 128K | Nvidia |
| nv-embed-v1 | — | 2024-06-07 | 33K | Nvidia |
| solar-10.7b-instruct | — | 2024-06-05 | 128K | Nvidia |
| Auto model | — | 2024-06-01 | 1.0M | NanoGPT |
| paligemma | — | 2024-05-14 | 128K | Nvidia |
| GPT-4o | — | 2024-05-13 | 128K | GitHub Models |
| Phi-3-small instruct (8k) | — | 2024-04-23 | 8K | GitHub Models |
| Phi-3-small instruct (128k) | — | 2024-04-23 | 128K | GitHub Models |
| Phi-3-medium instruct (128k) | — | 2024-04-23 | 128K | GitHub Models |
| Phi-3-mini instruct (4k) | — | 2024-04-23 | 4K | GitHub Models |
| Phi-3-medium instruct (4k) | — | 2024-04-23 | 4K | GitHub Models |
| Phi-3-mini instruct (128k) | — | 2024-04-23 | 128K | GitHub Models |
| Meta-Llama-3-70B-Instruct | — | 2024-04-18 | 8K | GitHub Models |
| Meta-Llama-3-8B-Instruct | — | 2024-04-18 | 8K | GitHub Models |
| Mistral: Mixtral 8x22B Instruct | — | 2024-04-17 | 66K | Nvidia |
| Cohere Command R | — | 2024-04-04 | 128K | GitHub Models |
| rerank-qa-mistral-4b | — | 2024-03-17 | 128K | Nvidia |
| esmfold | — | 2024-03-15 | 128K | Nvidia |
| BGE M3 | — | 2024-01-30 | 8K | Nvidia |
| Auto Route | — | 2024-01-01 | 128K | LLM Gateway |
| Custom Model | — | 2024-01-01 | 128K | LLM Gateway |
| Mistral: Mixtral 8x7B Instruct | — | 2023-12-10 | 33K | Nvidia |
| Whisper large-v3 | OpenAI | 2023-09-01 | — | Nvidia Privatemode AI |
| JAIS 30b Chat | — | 2023-08-30 | 8K | GitHub Models |
「免费」通常指免费额度或限时免费，可能附带速率限制与用量上限；商用前请确认各平台的服务条款。数据来自社区整理，仅供参考。