GPT-5.1 Model Specs, Costs & Benchmarks (July 2026)
GPT-5.1, developed by OpenAI, features a context window of 400K tokens. The model costs $1.25 per million tokens for input and $10.00 per million tokens for output. It was released on November 13, 2025, and has achieved impressive scores in various benchmarks.
Access GPT-5.1 & 210+ other AI models all in one platformTry Magica for free
Overview
 GPT-5.1 | |
|---|---|
Model Provider The organization behind this AI's development | OpenAI |
Input Context Window Maximum input tokens this model can process at once | 400K tokens |
Output Token Limit Maximum output tokens this model can generate at once | 128K tokens |
Release Date When this model first became publicly available | November 13, 2025 8 months ago November 13th, 2025 |
Pricing
| GPT-5.1 | |
|---|---|
Input Token Cost Cost per million input tokens | $1.25 per million tokens |
Output Token Cost Cost per million output tokens | $10.00 per million tokens |
Web Search Cost Additional cost for each web search operation | $0.01 per search |
Cache Read Cost Cost to reuse cached input tokens | $0.13 per million tokens |
Capabilities & Features
| GPT-5.1 | |
|---|---|
Input Types Supported input formats | imagetextfile |
Output Types Supported output formats | text |
Tokenizer Text encoding system | GPT |
Key Features Advanced capabilities | ✓ Function Calling✓ Structured Output✓ Reasoning Mode✓ Content Moderation |
Reasoning Controls Defaults and configurable reasoning effort | Enabled by defaultEffort: High, Medium, Low, NoneDefault: None |
Benchmarks
| GPT-5.1 | |
|---|---|
Intelligence Index Overall model quality across independent evaluations | 36.9 (Artificial Analysis index; higher is better) |
Coding Index Programming performance across independent evaluations | 49.4 (Artificial Analysis index; higher is better) |
Agentic Index Ability to complete multi-step agentic tasks | 21 (Artificial Analysis index; higher is better) |
Best Design Arena Score Highest human-preference Elo score across design arenas | 1,236 Elo (#36 in Game Dev (55.9% win rate)) |
Compare This Model
See how GPT-5.1 compares with other top models
Compare GPT-5.1 with top models in each category:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
