GPT-5.1 API

Try this model

GPT-5.1 is an incremental update to GPT-5 with improved accuracy and instruction adherence.

Modalities: Text, ImageText
In / Out price: $1.25/$10per 1M
Context window: 400K tokens
Released: Nov 14, 2025

GPT-5.1 overview

GPT-5.1 by OpenAI

It focuses on making the user experience more natural and the model’s reasoning behaviour more adaptive.

GPT-5.1 specs

Model ID: openai/gpt-5-1
Developer: OpenAI
Context window: 400,000 tokens
Max output: 128,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

GPT-5.1 API Overview

GPT-5.1 is an advanced iteration of the GPT-5 family by OpenAI. It improves on conversational quality, adaptive reasoning, and instruction-following capability, positioning itself as a more intelligent and user-friendly large language model suited for a variety of practical AI applications.

Technical Specifications

Architecture: Transformer-based neural network building on GPT-5 foundations, with presumed parameter count increases and optimized layer efficiency.
Context Window: Supports very long context input up to 128K tokens, enhancing long-form reasoning and document handling.
Inference: Runs distributed across GPU clusters, leveraging adaptive reasoning via a meta-controller that evaluates prompt complexity to dynamically allocate computational resources.
Safety & Robustness: Improved safeguard measures across harassment, hate speech, and image input evaluations, ensuring responsible AI usage.

Performance Benchmarks

Outperforms GPT-5 on key math and coding benchmarks such as AIME 2025 and Codeforces.
Demonstrates significant improvements in instruction adherence, response clarity, and conversational tone.

Output Quality & Reasoning Performance

Users report GPT-5.1 excels in maintaining coherent narratives over extended conversations with fewer contradictions. Its outputs balance creativity and reliability, yielding precise, contextually-aware responses with strong adherence to factual information.

Key Features

Adaptive Reasoning: Dynamically adjusts reasoning depth based on query complexity to balance speed and answer quality.
Improved Instruction Following: More reliable, clearer responses that align closely with user requests.
Personalization: Users can tailor ChatGPT’s tone and style with options including Default, Friendly, Efficient, Professional, Candid, Quirky, Nerdy, and Cynical, with further fine-tuning capabilities forthcoming.
Multimodal Support: Enhanced handling of various data types, including images and complex documents.
Long-Form Document Analysis: Supports extensive document contexts for deep analysis and summarization.

Practical Impact

GPT-5.1 is ideally suited for professional and research applications requiring deep reasoning, complex coding assistance, and multimodal content analysis. Its adaptability makes it valuable for interactive AI agents, automated research assistants, and creative collaborations.

Use cases

Everyday Chat and Assistance: Quick, natural conversational interactions using GPT-5.1 Instant.
Research and Data Analysis: Complex problem solving, coding help, and detailed textual and scientific analysis.
Content Creation: Drafting, summarizing, and brainstorming for marketing, presentations, or technical writing.
Multimodal Applications: Handling images, documents, and structured data for integrated workflows.
Personalized AI Experience: Custom tone and style settings for diverse user and organizational needs.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning
Web search

GPT-5.1 benchmarks by Artificial Analysis

See how GPT-5.1 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#72 / 219138Output tokens / second Latency#214 / 21644.49Seconds to first token Humanity's Last Exam#100 / 45828.5%Score GPQA Diamond#66 / 43987.3%Score

Speed

Output tokens / second

Benchmark results

Compare 16 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

GPT-5.1 API pricing

GPT-5.1 pricing in US dollars
Usage	Price	Unit
Input	$1.25	1M tokens
Output	$10	1M tokens
Cached input	$0.125	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

GPT-5.1 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
GPT-5.1	$1.25	$10
GPT-6 Luna	$0.1	$0.5
GPT-6.1 Terra	$1	$5
GPT-6.1 Sol	$2	$10
GPT-6.1 Terra Pro	$2.12	$10.58

How to use the GPT-5.1 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-5-1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "openai/gpt-5-1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-5-1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

GPT-5.1 FAQ

What is the context window of GPT-5.1?

GPT-5.1 has a 400,000 tokens context window and can return up to 128,000 tokens.

What inputs and outputs does GPT-5.1 support?

GPT-5.1 takes image, text as input and returns text.

What is the model ID for GPT-5.1?

Use openai/gpt-5-1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does GPT-5.1 cost?

GPT-5.1 costs $1.25 input and $10 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does GPT-5.1 support streaming?

Yes, GPT-5.1 can stream responses as they are generated.

Can GPT-5.1 read images?

Yes, GPT-5.1 accepts image input alongside text.

Who created GPT-5.1?

GPT-5.1 was built by OpenAI.

How can I access GPT-5.1 through the API?

Send requests to https://api.aimlapi.com/v1/chat/completions using the model id openai/gpt-5-1.

Does GPT-5.1 support function calling and tool use?

Yes, it supports function calling, parallel tool calls, and structured outputs.

Start building with GPT-5.1

Get API key

GPT-5.1 API

openai/gpt-5-1

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-5-1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "openai/gpt-5-1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "openai/gpt-5-1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

GPT-5.1 API

GPT-5.1 overview

GPT-5.1 by OpenAI

GPT-5.1 specs

GPT-5.1 API Overview

Technical Specifications

Performance Benchmarks

Output Quality & Reasoning Performance

Key Features

Practical Impact

Use cases

Capabilities

GPT-5.1 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GPT-5.1 API pricing

GPT-5.1 vs other models: token prices

How to use the GPT-5.1 API

Build with your agent

1Get your API key

2Make your first request

Related articles

GPT-5.1 FAQ

Start building with GPT-5.1

GPT-5.1 API

Build with your agent

1Get your API key

2Make your first request

GPT-5.1 API

GPT-5.1 overview

GPT-5.1 by OpenAI

GPT-5.1 specs

GPT-5.1 API Overview

Technical Specifications

Performance Benchmarks

Output Quality & Reasoning Performance

Key Features

Practical Impact

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

GPT-5.1 API pricing

GPT-5.1 vs other models: token prices

How to use the GPT-5.1 API

Build with your agent

1Get your API key

2Make your first request

Models similar to GPT-5.1

GPT-6.1 Terra

GPT-6.1 Terra Pro

GPT-6.1 Sol

Grok 4.20

Grok 4.3

Grok 4.20 Non-Reasoning

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

GPT-5.1 FAQ

Start building with GPT-5.1