Compare GPT-5.1-Codex-Mini from OpenAI and GPT-5.2 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.
GPT-5.1-Codex-Mini and GPT-5.2 Pro are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
GPT-5.1-Codex-Mini, from OpenAI, has a 400,000-token context window and is priced at $0.25/M tokens input, $2/M tokens output on OpenRouter.
GPT-5.2 Pro, from OpenAI, has a 400,000-token context window and is priced at $21/M tokens input, $168/M tokens output on OpenRouter.
| Attribute | GPT-5.1-Codex-Mini | GPT-5.2 Pro |
|---|---|---|
| Input price | $0.25/M tokens | $21/M tokens |
| Output price | $2/M tokens | $168/M tokens |
| Context window | 400,000 tokens | 400,000 tokens |
| Intelligence Index | 20.4 | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 4.91 s | 4.74 s |
| Throughput (p50) | 74.5 tok/s | 15.0 tok/s |
Benchmark data updated
GPT-5.1-Codex-Mini is cheaper than GPT-5.2 Pro on OpenRouter: GPT-5.1-Codex-Mini costs $0.25/M tokens input and $2/M tokens output, while GPT-5.2 Pro costs $21/M tokens input and $168/M tokens output.
GPT-5.1-Codex-Mini and GPT-5.2 Pro have the same context window of 400,000 tokens.
GPT-5.1-Codex-Mini is faster on OpenRouter, generating a median 74.5 tokens per second compared with 15.0 tokens per second for GPT-5.2 Pro.