Anthropic Claude Sonnet 5.5 vs OpenAI GPT-5.1-Codex
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- GPT-5.1-Codex is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- Claude Sonnet 5.5 accepts longer prompts: 1M vs 400K tokens.
- Claude Sonnet 5.5 is the newer model (released 2026-09-28).
| Claude Sonnet 5.5 | GPT-5.1-Codex | |
|---|---|---|
| Vendor | Anthropic | OpenAI |
| Released | 2026-09-28 | 2025-11-13 |
| Input / 1M | $2.00 | $1.25 |
| Output / 1M | $10.00 | $10.00 |
| Cached input / 1M | $0.10 | $0.13 |
| Blended / 1M (3:1) | $4.00 | $3.44 |
| Context | 1M | 400K |
| Max output | 128K | 128K |
| Accepts | text, image, file | text, image |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 8 | 1 |
| Cheapest provider, output | $10.00 | $10.00 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Claude Sonnet 5.5
$270 per month$9.00 per day
GPT-5.1-Codex
$225 per month$7.50 per day
GPT-5.1-Codex saves $45.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Claude Sonnet 5.5 with