OpenAI model product
GPT-5.1
The best model for coding and agentic tasks with configurable reasoning effort.
Updated Aug 12, 2026. Default version: GPT-5.1
LLMBoard score62.1GPT-5.1
Coverage60%9 benchmark families
Context window400KTokens
Official input price$1.25OpenAI API
GPT-5.1 Specifications
Technical details for the model's default version.
- Version
- GPT-5.1
- Released
- Nov 13, 2025
- Knowledge cutoff
- Sep 30, 2024
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.1 Benchmark Results
Benchmark scores for GPT-5.1.
| MMMU | 85.4% | 02 | 63 | 98.4% | C | |
| BrowseComp Long Context 128k | 90.0% | 03 | 5 | 50.0% | C | |
| Tau2 Airline | 67.0% | 04 | 23 | 86.4% | C | |
| FrontierMath | 26.7% | 08 | 17 | 56.3% | C | |
| Tau2 Retail | 77.9% | 10 | 26 | 64.0% | C | |
| Tau2 Telecom | 95.6% | 10 | 35 | 73.5% | C | |
| AIME 2025 | 94.0% | 25 | 114 | 78.8% | C | |
| SWE-Bench Verified | 76.3% | 30 | 105 | 72.1% | C | |
| GPQA | 88.1% | 32 | 234 | 86.7% | C |
GPT-5.1 Arena Results
Preference and agent-evaluation results for the default version.
| search factuality | overall | 08 | 1203.8 | 59,855 | N/A | |
| search | overall | 12 | 1199.4 | 60,019 | N/A | |
| search style control | overall | 19 | 1183.6 | 60,019 | N/A | |
| document | overall | 37 | 1400.8 | 8,220 | N/A | |
| document style control | overall | 37 | 1411.7 | 8,220 | N/A | |
| vision style control | overall | 49 | 1238.5 | 10,016 | N/A | |
| vision | overall | 58 | 1233.0 | 10,016 | N/A | |
| text factuality | overall | 62 | 1445.5 | 42,748 | N/A | |
| text style control | overall | 77 | 1438.7 | 43,654 | N/A | |
| webdev | overall | 82 | 1340.6 | 10,352 | N/A | |
| text | overall | 90 | 1422.3 | 43,654 | N/A |
GPT-5.1 Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.1. Runtime does not affect the capability score.
| OpenAI | 226.81 tok/s | 0.829 s | 400K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.25 input, $10 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $1.25 input, $10 output per 1M via Impossibl
- Tracked offerings
- 16
| Impossibl | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| NanoGPT | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| NEAR AI Cloud | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| ZenMux | openai/gpt-5.1-chat | global | $1.25 | $10 | 128K | |
| ZenMux | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| Ofox | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| OrcaRouter | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| OrcaRouter | openai/gpt-5.1-chat-latest | global | $1.25 | $10 | 128K | |
| Kilo Gateway | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| Merge Gateway | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| Merge Gateway | openai/gpt-5.1-chat-latest | global | $1.25 | $10 | 128K | |
| OpenRouter | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| Cloudflare AI Gateway | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| Perplexity Agent | openai/gpt-5.1 | global | $1.25 | $10 | 400K | |
| OpenAI | gpt-5.1 | global | $1.25 | $10 | 400K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-5.1 | 62.1 | N/A | 400K | 128K | No | Proprietary | |
| GPT-5.1 High | N/A | N/A | 400K | 128K | No | Proprietary | |
| GPT-5.1 Medium | N/A | N/A | 400K | 128K | No | Proprietary | |
| GPT-5.1 Thinking | N/A | N/A | 400K | 128K | No | Proprietary |
What is GPT-5.1?
Key information about GPT-5.1 and its available data.
The best model for coding and agentic tasks with configurable reasoning effort. 1 is our flagship model for coding and agentic tasks with configurable reasoning and non-reasoning effort.
Data as of 2026-08-11.
GPT-5.1 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-5.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.3-Codex
OpenAI
OP
GPT-5.1-Instant
OpenAI
OP
GPT-5.4-mini
OpenAI
OP
GPT-5.2-Codex
OpenAI
OP
GPT-5.5-Instant
OpenAI
OP
GPT-5.2
OpenAI
FAQ
Common questions about GPT-5.1.
When was GPT-5.1 released?
GPT-5.1's default version was released on Nov 13, 2025.
How much does GPT-5.1 cost?
GPT-5.1's official API price is $1.25 per million input tokens and $10 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.25 input and $10 output via Impossibl.
Who created GPT-5.1?
GPT-5.1 was created by OpenAI.
What is the context window for GPT-5.1?
The default version has a 400K token context window.
Is GPT-5.1 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.1?
16 provider offerings are linked to the default version.
What models should I compare GPT-5.1 with?
Nearby ranked alternatives include MiMo V2 Pro, GPT-5.3-Codex, Nemotron 3 Ultra.