GPT-5.1
OpenAI's flagship model for coding and agentic tasks with configurable reasoning and no-reasoning modes.
Pricing
Input$1.25 / 1M checked Jul 19, 2026
Cached input$0.125 / 1M
Output$10 / 1M checked Jul 19, 2026
Batch pricing is available; tools can add separate fees.
Cost bandPremium
Free tierNo free API tier.
Limits
Context window400k checked Jul 19, 2026
Max output128k
Knowledge cutoffSep 30, 2024
DeploymentOpenAI API
OpenAI-compatible APIYes
ModalitiesText, Image input
Where it fits
Best forCoding agents, tool orchestration, high-stakes workflows that need one general-purpose flagship.
Business fitPremium choice when code quality and agent reliability matter more than raw token cost.
Capabilities
Adaptive reasoningFunction callingStructured outputsWeb searchFile searchCode interpreterMCP
Benchmark scores
Composite91 / 100
Coding93 / 100 (SWE-bench Verified)
Reasoning90 / 100 (GPQA Diamond)
Long context88 / 100 (RULER 128K)
Vision86 / 100 (MMMU)
Instruction following94 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Nov 1, 2025. These are not independent measurements run by this site.
Change history
- Nov 13, 2025New modelGPT-5.1 released 400k context, configurable reasoning modes. OpenAI's new flagship for coding and agentic workflows.
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/openai/gpt-5.1
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.