- Providers
- OpenAI
OpenAI: API pricing, speed & models
OpenAI hosts 32 active AI models, with input pricing from $0.10 per 1M tokens, with median throughput of 207 characters/sec, and P95 time to first token of 9.19s, with 98.5% success rate over 7 days. Compare OpenAI's API speed, pricing, and reliability against other inference providers.
Image generationVideoFirst-party only
Median throughput207 c/s
Median TTFT2.15s
P95 TTFT9.19s
Success rate (7d)98.5%
From$0.10 /M tok
Catalog
Type
Price
67 models| Model |
|---|
GPT-5.6 Lunacache pricing |
GPT-5.6 Lunacache pricing |
GPT-5.6 Terracache pricing |
GPT-5.6 Terracache pricing |
GPT-5.6 Solcache pricing |
GPT-5.6 Solcache pricing |
GPT-5.5cache pricing |
GPT-5.5cache pricing |
GPT-5.450 QPS |
GPT-5.450 QPS |
GPT-5.5 Instant100 QPS |
GPT-5.5 Instant100 QPS |
GPT-5.3 Chat100 QPS |
GPT-5.3 Chat100 QPS |
GPT-5.3 Codex50 QPS |
GPT-5.3 Codex50 QPS |
GPT-5.2 Codex50 QPS |
GPT-5.2 Codex50 QPS |
GPT-5.1 Medium90 QPS |
GPT-5.1 Medium90 QPS |
GPT-5.2100 QPS |
GPT-5.2100 QPS |
GPT-5.1100 QPS |
GPT-5.1100 QPS |
GPT-5.1 Instant100 QPS |
GPT-5.1 Instant100 QPS |
GPT-5 mini200 QPS |
GPT-5 mini200 QPS |
GPT-4 Turbo100 QPS |
GPT-4o132 QPS |
GPT-4o132 QPS |
GPT-4o100 QPS |
GPT-4o100 QPS |
GPT-4.1 nano200 QPS |
GPT-4.1 nano200 QPS |
GPT-4.1 mini150 QPS |
GPT-4.1 mini150 QPS |
GPT-4.1100 QPS |
GPT-4.1100 QPS |
GPT-3.5 Turbo100 QPS |