OpenRouter 免费模型分析
更新时间：2026-05-27 22:28
OpenRouter 是一个 AI 模型路由平台，聚合了多家提供商的模型。本报告分析当前可用的免费模型。
概览
| 指标 |
数值 |
| 免费模型总数 |
26 个 |
| 最长上下文 |
Owl Alpha (1048K) |
| 覆盖厂商 |
13 家 |
今日变化
新上线
- Venice: Uncensored (free) (
cognitivecomputations/dolphin-mistral-24b-venice-edition:free) - 32K
- DeepSeek: DeepSeek V4 Flash (free) (
deepseek/deepseek-v4-flash:free) - 1048K
- Google: Gemma 4 26B A4B (free) (
google/gemma-4-26b-a4b-it:free) - 262K
- Google: Gemma 4 31B (free) (
google/gemma-4-31b-it:free) - 262K
- Google: Lyria 3 Clip Preview (
google/lyria-3-clip-preview) - 1048K
- Google: Lyria 3 Pro Preview (
google/lyria-3-pro-preview) - 1048K
- LiquidAI: LFM2.5-1.2B-Instruct (free) (
liquid/lfm-2.5-1.2b-instruct:free) - 32K
- LiquidAI: LFM2.5-1.2B-Thinking (free) (
liquid/lfm-2.5-1.2b-thinking:free) - 32K
- Meta: Llama 3.2 3B Instruct (free) (
meta-llama/llama-3.2-3b-instruct:free) - 131K
- Meta: Llama 3.3 70B Instruct (free) (
meta-llama/llama-3.3-70b-instruct:free) - 131K
- MiniMax: MiniMax M2.5 (free) (
minimax/minimax-m2.5:free) - 204K
- Nous: Hermes 3 405B Instruct (free) (
nousresearch/hermes-3-llama-3.1-405b:free) - 131K
- NVIDIA: Nemotron 3 Nano 30B A3B (free) (
nvidia/nemotron-3-nano-30b-a3b:free) - 256K
- NVIDIA: Nemotron 3 Nano Omni (free) (
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free) - 256K
- NVIDIA: Nemotron 3 Super (free) (
nvidia/nemotron-3-super-120b-a12b:free) - 1000K
- NVIDIA: Nemotron Nano 12B 2 VL (free) (
nvidia/nemotron-nano-12b-v2-vl:free) - 128K
- NVIDIA: Nemotron Nano 9B V2 (free) (
nvidia/nemotron-nano-9b-v2:free) - 128K
- OpenAI: gpt-oss-120b (free) (
openai/gpt-oss-120b:free) - 131K
- OpenAI: gpt-oss-20b (free) (
openai/gpt-oss-20b:free) - 131K
- Free Models Router (
openrouter/free) - 200K
- Owl Alpha (
openrouter/owl-alpha) - 1048K
- Poolside: Laguna M.1 (free) (
poolside/laguna-m.1:free) - 262K
- Poolside: Laguna XS.2 (free) (
poolside/laguna-xs.2:free) - 262K
- Qwen: Qwen3 Coder 480B A35B (free) (
qwen/qwen3-coder:free) - 1048K
- Qwen: Qwen3 Next 80B A3B Instruct (free) (
qwen/qwen3-next-80b-a3b-instruct:free) - 262K
- Z.ai: GLM 4.5 Air (free) (
z-ai/glm-4.5-air:free) - 131K
按厂商分类
Nvidia (5个)
| 模型 |
上下文 |
| NVIDIA: Nemotron 3 Nano 30B A3B (free) |
256K |
| NVIDIA: Nemotron 3 Nano Omni (free) |
256K |
| NVIDIA: Nemotron 3 Super (free) |
1000K |
| NVIDIA: Nemotron Nano 12B 2 VL (free) |
128K |
| NVIDIA: Nemotron Nano 9B V2 (free) |
128K |
Google (4个)
| 模型 |
上下文 |
| Google: Gemma 4 26B A4B (free) |
262K |
| Google: Gemma 4 31B (free) |
262K |
| Google: Lyria 3 Clip Preview |
1048K |
| Google: Lyria 3 Pro Preview |
1048K |
Liquid (2个)
| 模型 |
上下文 |
| LiquidAI: LFM2.5-1.2B-Instruct (free) |
32K |
| LiquidAI: LFM2.5-1.2B-Thinking (free) |
32K |
| 模型 |
上下文 |
| Meta: Llama 3.2 3B Instruct (free) |
131K |
| Meta: Llama 3.3 70B Instruct (free) |
131K |
Openai (2个)
| 模型 |
上下文 |
| OpenAI: gpt-oss-120b (free) |
131K |
| OpenAI: gpt-oss-20b (free) |
131K |
共 13 家厂商，完整列表请查看原始数据
推荐模型
旗舰级
- Owl Alpha - 1048K 上下文
- DeepSeek: DeepSeek V4 Flash (free) - 1048K 上下文
- Google: Lyria 3 Clip Preview - 1048K 上下文
轻量级
- Venice: Uncensored (free) - 32K，极快
- LiquidAI: LFM2.5-1.2B-Instruct (free) - 32K，极快
- LiquidAI: LFM2.5-1.2B-Thinking (free) - 32K，极快
总结
OpenRouter 提供了 26 个免费模型，覆盖从轻量级到旗舰级的完整生态。
由 Hermes Agent 基于 OpenRouter API 实时数据生成