Discover free LLM API models across providers with real speed and latency benchmarks.
LMSpeed tracks 234 LLM models available for free across 39 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 |
|---|---|---|---|---|
microsoft/phi-3-mini-4k-instructGitHub ModelsFREE ReasoningToolsOpen Weights4.1KPhi-3-mini instruct (4k) is an AI model provided by github-models. | N/A | N/A | 0 | |
microsoft/phi-3-small-128k-instructNvidiaFREE ToolsFilesOpen WeightsVisionPhi 3 Small 128k Instruct is an AI model provided by nvidia. | N/A |
| N/A |
| 0 |
microsoft/phi-3-small-8k-instructNvidiaFREE ToolsFilesOpen WeightsVisionPhi 3 Small 8k Instruct is an AI model provided by nvidia. | N/A | N/A | 0 |
mistralai/mamba-codestral-7b-v0.1NvidiaFREE Open Weights128KMamba Codestral 7b V0.1 is an AI model provided by nvidia. | N/A | N/A | 0 |
mistralai/mistral-small-3.1-24b-instruct-2503NvidiaFREE ToolsOpen Weights128KMistral Small 3.1 24b Instruct 2503 is an AI model provided by nvidia. | N/A | N/A | 0 |
qwen/qwen2.5-coder-32b-instructNvidiaFREE ToolsOpen Weights128KQwen2.5 Coder 32b Instruct is an AI model provided by nvidia. | N/A | N/A | 0 |
qwen/qwen3.5-397b-a17bFREE ReasoningToolsFilesOpen WeightsQwen3.5 397B A17B is an AI model provided by openrouter. | N/A | N/A | 0 |
z-ai/glm5FREE ReasoningToolsOpen Weights202.8KGLM5 is an AI model provided by nvidia. | N/A | N/A | 0 |
Open Weights512bge-reranker-v2-m3 is an AI model provided by berget. | N/A | N/A | 0 |
ToolsOpen Weights262.1KKimi K2 0905 is an AI model provided by nvidia. | N/A | N/A | 0 |
MiniMax-M2FREE ReasoningToolsOpen Weights128KMiniMax-M2 is an AI model provided by nvidia. | N/A | N/A | 0 |
MiniMax-M2.1FREE ReasoningToolsOpen Weights204.8KMiniMax-M2.1 is an AI model provided by nvidia. | N/A | N/A | 0 |
ReasoningToolsOpen Weights204.8KMiniMax-M2.5 is an AI model provided by nvidia. | N/A | N/A | 0 |
