Compare LLM API pricing and speed benchmarks across 100+ providers — OpenAI, DeepSeek, Claude, Gemini, and more. Find the cheapest and fastest API for your project.
| Time | Provider | Model | Speed | Latency |
|---|---|---|---|---|
| Apr 17, 12:50 AM | platform.aitools.cfd | zhipu/glm-4-flash | 34.65t/s | 1.15s |
| Apr 16, 09:05 PM | platform.aitools.cfd | zhipu/glm-4-flash | 33.28t/s | 0.84s |
| Apr 16, 09:01 PM | platform.aitools.cfd | zhipu/glm-4-flash | 39.25t/s | 0.69s |
| Apr 16, 08:26 PM | platform.aitools.cfd | qwen/qwen3-8b | 26.08t/s | 33.74s |
| Apr 16, 08:18 PM | platform.aitools.cfd | zhipu/glm-4-flash | 34.54t/s | 0.64s |
Compare API pricing per token, run speed benchmarks, and find the best provider for your AI application.
Compare per-token API pricing across 100+ providers side by side. Find the cheapest LLM API for any model, with free tier and credits tracking.
Run standardized speed benchmarks measuring API throughput and latency with multi-prompt testing
Benchmark any API endpoint with custom base URLs and API keys — official providers, proxies, and self-hosted models
Detailed speed benchmark metrics including first token latency, output throughput, and processing time across providers
Monitor benchmark progress in real-time with streaming results for each prompt evaluation
Learn more about LMSpeed
LMSpeed aggregates per-token pricing from 100+ API providers. Visit any model page to see a side-by-side pricing comparison table showing input and output rates per million tokens, so you can find the cheapest provider for each model.
Many providers offer free API tiers or credits for popular models like DeepSeek, Gemini, and Llama. Check our Free LLM API directory for a complete list of models with free access, including speed benchmarks for each free provider.
LMSpeed employs a five-round continuous stress testing mechanism with standardized prompts. Token calculations are performed accurately using tiktoken, measuring output throughput (tokens per second) and first-token latency.
Use our performance leaderboards and model detail pages to visually compare API speed benchmarks across providers. The system ranks providers by throughput, latency, and health, helping you choose the fastest and most reliable API.
Coming soon
