Skip to content
Dashboard

GPT 5.1 Thinking

GPT 5.1 Thinking is the reasoning-focused member of the GPT-5.1 family, applying extended chain-of-thought computation to produce more thorough and accurate responses on complex analytical, scientific, and multi-step problems.

View API reference
Input and output price
Prices from: Input $1.25, Output $10, Per 1M tokens
24h uptime
Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({
model: 'openai/gpt-5.1-thinking',
prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingPlayground

Try out GPT 5.1 Thinking by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

openai logo
openai logo

GPT 5.1 Thinking

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Free Tier
Release Date
400K128K1.5 s107 tps
$1.25/M+2 more
$10/M+2 more
Read$0.13/M
$10/K
+3
11/12/2025
400K128K0.9 s
$1.25/M
$10/M
Read$0.13/M
$14/K
+3
11/12/2025

Copy link to headingUptime

Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.

Copy link to headingThroughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Copy link to headingLatency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.

Getting started

Call GPT 5.1 Thinking through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
prompt: 'Why is the sky blue?',
});
console.log(result.text);
}
main().catch(console.error);

Top-level parameters

The same GPT 5.1 Thinking request in each API format AI Gateway supports.

top-level-params.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
system: 'You are a concise technical assistant.',
prompt: 'Summarize the tradeoffs between static generation and SSR.',
maxOutputTokens: 1024,
});
console.log(result.text);
}
main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. openai/gpt-5.1-thinking. AI Gateway routes the request to an available provider.
maxOutputTokensnumberNoHard cap on generated tokens. GPT 5.1 Thinking supports up to 128,000 output tokens. Reasoning tokens count toward this limit.
reasoning'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'NoProvider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below.
providerOptionsRecord<string, JSONValue>NoAI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

InputFormatsSourcesMax countMax sizeLimits
TextPrompt and response share the 400K-token context window
ImageURL, base64, Uint8ArraySent as image parts in messages; counts as input tokens
PDFURL, base64, Uint8ArraySent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK openai provider docs.

provider-options.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
prompt: 'Why is the sky blue?',
providerOptions: {
gateway: {
only: ['openai', 'azure'],
},
},
});
console.log(result.text);
}
main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

ParameterTypeRequiredDescription
providerOptions.gateway.onlystring[]NoRestrict routing to these provider slugs. Requests fail over only within the listed providers.
providerOptions.gateway.orderstring[]NoPreferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
providerOptions.gateway.sort'cost' | 'ttft' | 'tps'NoRank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
providerOptions.gateway.zeroDataRetentionbooleanNoRoute only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
prompt: 'Explain the Monty Hall problem step by step.',
reasoning: 'high',
});
console.log(result.text);
}
main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe this image.' },
{ type: 'image', image: 'https://example.com/photo.jpg' },
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Summarize this document.' },
{
type: 'file',
mediaType: 'application/pdf',
data: 'https://example.com/document.pdf',
},
],
},
],
});
console.log(result.text);
}
main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts
import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking',
prompt: 'What is the weather in San Francisco?',
tools: {
getWeather: tool({
description: 'Get the current weather for a location',
inputSchema: z.object({ location: z.string() }),
execute: async ({ location }) => ({ location, temperatureC: 18 }),
}),
},
});
console.log(result.text);
}
main().catch(console.error);

Fast mode

GPT 5.1 Thinking can run in fast mode for lower latency by appending -fast to the model ID.

fast-mode.ts
import { generateText } from 'ai';
import 'dotenv/config';
async function main() {
const result = await generateText({
model: 'openai/gpt-5.1-thinking-fast',
prompt: 'Why is the sky blue?',
});
console.log(result.text);
}
main().catch(console.error);

Copy link to headingMore models by OpenAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Free Tier
Release Date
1.1M2.9 s56 tps
$10/M+2 more
$50/M+2 more
Read$1/M
Write$12.50/M
$10/K
+4
azure logo
openai logo
09/04/2026
1.1M2.4 s156 tps
$0.20/M+2 more
$1.20/M+2 more
Read$0.02/M
Write$0.25/M
$10/K
+4
azure logo
bedrock logo
openai logo
07/09/2026
1.1M2.6 s69 tps
$2/M+2 more
$10/M+2 more
Read$0.20/M
Write$2.50/M
$10/K
+4
azure logo
bedrock logo
openai logo
07/09/2026
1.1M2.6 s94 tps
$2/M+2 more
$12/M+2 more
Read$0.20/M
Write$2.50/M
$10/K
+4
azure logo
bedrock logo
openai logo
07/09/2026
1.1M3.5 s88 tps
$2.50/M+2 more
$15/M+2 more
Read$0.25/M
$10/K
+4
azure logo
openai logo
03/05/2026
400K4.4 s208 tps
$0.05/M
$0.40/M
Read$0.005/M
$14/K
+3
azure logo
openai logo
08/07/2025

Copy link to headingAbout GPT 5.1 Thinking

GPT 5.1 Thinking was released on November 12, 2025 as part of the GPT-5.1 model generation on AI Gateway. It occupies the reasoning-depth end of the GPT-5.1 spectrum, complementing the speed-optimized instant variant.

The model uses extended chain-of-thought computation, generating internal reasoning tokens that work through problems step by step before producing a visible response. This approach, proven effective in the o-series models, is here applied within the GPT-5.1 architecture to produce more accurate and thorough answers on complex problems.

The context window of 400K tokens supports the lengthy inputs that complex reasoning tasks often require, whether they are research papers, detailed problem statements, or extensive codebases that need architectural analysis. Longer response times come in exchange for deeper, more reliable reasoning.

Copy link to headingWhat To Consider When Choosing a Provider

  • Configuration: GPT 5.1 Thinking generates internal reasoning tokens before producing its final response, similar to the o-series reasoning models but within the GPT-5.1 architecture. This produces better results on hard problems at the cost of longer response times.
  • Configuration: Use GPT 5.1 Thinking for your hardest queries and GPT-5.1 instant for everything else. A routing layer can direct traffic based on query complexity.
  • Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use GPT 5.1 Thinking

Best for

  • Complex analysis: Multi-step research, data analysis, and strategic reasoning that benefits from deliberation
  • Mathematical problem solving: Proofs, derivations, and quantitative analysis requiring verified steps
  • Scientific reasoning: Physics, chemistry, and biology problems with multi-step logical chains
  • Hard coding problems: Algorithm design, optimization, and architectural decisions requiring extended thought
  • Extended chain-of-thought: The GPT-5.1 generation's deliberation tier, complementing the speed-optimized instant variant

Consider alternatives when

  • Fast responses needed: GPT-5.1 instant for real-time interactions
  • Coding agent workflows: GPT-5.1 codex family for autonomous software engineering
  • Pure STEM reasoning: The o-series reasoning models for the deepest chain-of-thought capability in OpenAI's lineup
  • General chat: GPT-5.1 instant for conversational workloads where reasoning depth is unnecessary

GPT 5.1 Thinking brings extended reasoning to the GPT-5.1 family, producing more thorough and accurate results on complex problems. For analytical, scientific, and multi-step tasks routed through AI Gateway, it is the depth-focused counterpart to the speed-optimized instant variant.

Copy link to headingFrequently Asked Questions

  • How does GPT 5.1 Thinking reasoning work?

    It generates internal reasoning tokens that work through the problem step by step before producing a visible response, similar to the approach used in o-series reasoning models.

  • When should I use thinking versus instant?

    Use thinking for complex analysis, math, science, and hard coding problems where accuracy is the priority. Use instant for real-time chat, streaming content, and tasks where speed is the priority.

  • Is GPT 5.1 Thinking slower than GPT-5.1 instant?

    Yes. The extended reasoning process adds time before the first visible output. The tradeoff is deeper, more accurate reasoning on complex problems.

  • What context window does GPT 5.1 Thinking support?

    400K tokens, supporting the lengthy inputs that complex reasoning tasks often require.

  • How does AI Gateway handle authentication for GPT 5.1 Thinking?

    AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.

  • What are typical latency characteristics?

    This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

Your use is subject to OpenAI's Terms & Privacy Policies.