OpenAI · Released Dec 4, 2025
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...
- Top 30%Terminal-Bench
- Top 31%METR time horizon
- Released
- Dec 4 2025
- Context window
- 400K 128K out
- Input / 1M tokens
- $1.25 from $1.10
- Output / 1M tokens
- $10.00 from $9.00
Where to run it
14 providers compared
Cheapest: Poe at $1.10 / $9.00 per 1M input / output tokens — 67% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Poe | $1.10 | $9.00 | $0.11 | 400K | 128K | — | Cheapest |
| Jiekou.AI | $1.19 | $9.50 | $0.12 | 400K | 128K | — | +6% |
| Azure | $1.25 | $10.00 | $0.13 | 400K | 128K | 100%24h | +12% |
| Kilo Gateway | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| Vercel AI Gateway | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| DigitalOcean | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| Azure Cognitive Services | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| Vivgrid | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| Abacus | $1.25 | $10.00 | — | 400K | 128K | — | +12% |
| Ofox | $1.25 | $10.00 | $0.13 | 256K | 128K | — | +12% |
| OpenCode | $1.25 | $10.00 | $0.13 | 400K | 128K | — | +12% |
| Eden AI | $1.25 | $10.00 | $0.13 | 272K | 128K | — | +12% |
| NanoGPT | $2.50 | $20.00 | $0.25 | 400K | 128K | — | +124% |
| AI/ML API | $3.44 | $27.51 | $0.34 | 400K | 128K | — | +208% |
Value
Price vs. performance
GPT-5.1-Codex-Max 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
3 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 60.5% | #12of 40 | GPT-5.584.7% |
| METR time horizonSoftware engineering · Length of software task solved more often than not | 3.7 h | #7of 23 | Claude Opus 4.612 h |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 9.0% | #65of 70 | Claude Sonnet 5.5100.0% |
Specs
Details
- Model ID
openai/gpt-5.1-codex-max- Developer
- OpenAI
- Release date
- Dec 4, 2025 ·
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- API price
- $1.25 / $10.00 per 1M input / output tokens
- Providers
- 14
- 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.