OpenAI · Released Nov 13, 2025
GPT-5.1-Codex
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
- Top 33%Terminal-Bench
- Released
- Nov 13 2025
- Context window
- 400K 128K out
- Input / 1M tokens
- $1.25 from $1.07
- Output / 1M tokens
- $10.00 from $8.50
Where to run it
18 providers compared
Cheapest: OpenCode at $1.07 / $8.50 per 1M input / output tokens — 15% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| OpenCode | $1.07 | $8.50 | $0.11 | 400K | 128K | — | Cheapest |
| Poe | $1.10 | $9.00 | $0.11 | 400K | 128K | — | +5% |
| Jiekou.AI | $1.19 | $9.50 | $0.12 | 400K | 128K | — | +12% |
| Azure | $1.25 | $10.00 | $0.13 | 400K | 128K | 100%24h | +17% |
| AIHubMix | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| LLM Gateway | $1.25 | $10.00 | — | 400K | 272K | — | +17% |
| ZenMux | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Helicone | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| OrcaRouter | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Vivgrid | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Impossibl | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| NanoGPTno tool calling | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Kilo Gateway | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| DevPass (LLM Gateway) | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Azure Cognitive Services | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Abacus | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Vercel AI Gateway | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +17% |
| Eden AI | $1.25 | $10.00 | $0.13 | 272K | 128K | — | +17% |
Value
Price vs. performance
GPT-5.1-Codex Other OpenAI Other labs Value frontier · Terminal-Bench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
2 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 57.8% | #13of 40 | GPT-5.584.7% |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1336 | #79of 90 | Claude Opus 5.51820 |
Specs
Details
- Model ID
openai/gpt-5.1-codex- Developer
- OpenAI
- Release date
- Nov 13, 2025 ·
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- API price
- $1.25 / $10.00 per 1M input / output tokens
- Providers
- 18
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.