Claude Haiku 4.5 vs GPT-5.1-Codex-Mini
Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and GPT-5.1-Codex-Mini (OpenAI). Green cells mark the better value in each row.
Prices updated Jul 22, 2026, 1:38 AM UTC · refreshed hourly
| Claude Haiku 4.5 Anthropic | GPT-5.1-Codex-Mini OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $0.25 |
| Output $/1M | $5.00 | $2.00 |
| Blended $/1M (3:1) | $2.00 | $0.688 |
| RAG example (30K in / 2K out) | $0.04 | $0.0115 |
| Quality & speed | ||
| Intelligence Index | 29.6 | 30.6 |
| Coding Index | 43.9 | — |
| Agentic Index | 16.4 | — |
| Output speed (tok/s) | — | 210 |
| Time to first token | — | 4.92s |
| Specs | ||
| Context window | 200K | 400K |
| Input modalities | text, image, file | image, text |
FAQ
Which is cheaper, Claude Haiku 4.5 or GPT-5.1-Codex-Mini?
GPT-5.1-Codex-Mini has the lower blended API price at $0.688 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), GPT-5.1-Codex-Mini costs about $0.0115 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and GPT-5.1-Codex-Mini offers 400K.
Which scores higher on Artificial Analysis benchmarks?
GPT-5.1-Codex-Mini leads on the Artificial Analysis Intelligence Index (30.6 vs 29.6). Check coding and agentic indices on this page for workload-specific tradeoffs.