Compare o3 Mini from OpenAI and o3 Pro from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
o3 Mini and o3 Pro are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
o3 Mini, from OpenAI, has a 200,000-token context window and is priced at $1.10/M tokens input, $4.40/M tokens output on OpenRouter.
o3 Pro, from OpenAI, has a 200,000-token context window and is priced at $20/M tokens input, $80/M tokens output on OpenRouter.
| Attribute | o3 Mini | o3 Pro |
|---|---|---|
| Input price | $1.10/M tokens | $20/M tokens |
| Output price | $4.40/M tokens | $80/M tokens |
| Context window | 200,000 tokens | 200,000 tokens |
| Intelligence Index | 12.5 | 21.9 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 2.52 s | 5.17 s |
| Throughput (p50) | 113.0 tok/s | 14.5 tok/s |
Benchmark data updated
o3 Mini is cheaper than o3 Pro on OpenRouter: o3 Mini costs $1.10/M tokens input and $4.40/M tokens output, while o3 Pro costs $20/M tokens input and $80/M tokens output.
o3 Mini and o3 Pro have the same context window of 200,000 tokens.
o3 Mini is faster on OpenRouter, generating a median 113.0 tokens per second compared with 14.5 tokens per second for o3 Pro.