Discover free LLM API models across providers with real speed and latency benchmarks.
LMSpeed tracks 244 LLM models available for free across 40 API providers. Free tiers vary by provider — some offer limited daily requests, others provide free credits for new users. All speed data is from real API tests.
| Model | Providers | Speed | Latency | Tests |
|---|---|---|---|---|
OpenAIFREE | 30.05 t/s | 4.72 s | 5 | |
OpenAIFREE | 123.38 t/s | 8.53 s | 5 | |
FREE | 20.72 t/s | 1.47 s | 5 | |
OpenAIFREE Reasoning |
| N/A |
| N/A |
| 0 |
| N/A | N/A | 0 |
开源国产由阿里巴巴开发的Qwen系列模型！
国产开源大模型中的佼佼者！ | N/A | N/A | 0 |
| N/A | N/A | 0 |
开源国产开源权重32KQwen 3 Embedding 8B 是由 huggingface 提供的人工智能模型。 | N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
GPT-5.2 是 OpenAI 的旗舰级通用智能模型，具备更高的推理能力、准确性、记忆与多模态处理能力，适用于复杂任务和智能代理开发。-none（默认）、-low、-medium、-high、-xhigh 后缀的模型分别为该模型对应的推理（effort）参数，以便适配各种客户端，实际模型均为 gpt-5.2。 | N/A | N/A | 0 |
| N/A | N/A | 0 |
qwen/qwen3.5-397b-a17b阿里巴巴FREE ReasoningToolsFilesOpen WeightsQwen3.5 397B A17B is an AI model provided by openrouter. | N/A | N/A | 0 |
李/google/gemma-3n-e2b-itGoogleFREE | N/A | N/A | 0 |
李/google/gemma-3n-e4b-itGoogleFREE | N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
| N/A | N/A | 0 |
ReasoningTools文件MultimodalGPT-5.1 Codex Max 是由 opencode 提供的人工智能模型。 | N/A | N/A | 0 |
