OpenAI: GPT-5.1
gpt-5.1- Input / Output-30%
- $1.25 / $10.00$0.875 / $7.00
- Context
- 410K
- Max output
- 128K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt Cache
About GPT-5.1
GPT-5.1 is OpenAI's flagship model of its generation for coding and agentic tasks, with configurable reasoning and non-reasoning effort. Setting effort to none turns it into a fast, non-reasoning model; higher levels bring reasoning back. It takes text and images and supports function calling, structured outputs, web search, and MCP. It follows GPT-5 and precedes GPT-5.2.
Where it works well
- Reasoning effort can be set to none, low, medium, or high, so one model serves both fast and deliberate turns.
- Described by OpenAI as its flagship for coding and agentic tasks at release.
- Accepts text and image input and supports structured outputs and function calling.
- Supports prompt caching, web search, a code interpreter, and MCP tools.
When to choose another model
- Knowledge ends in September 2024, earlier than GPT-5.2 and later models.
- It has no xhigh effort level, which newer models add for the hardest problems.
- It returns text only, never images or audio.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-5.1", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Default spec
per 1M tokens- Official price
- Input $1.25 / Output $10.00 / Cache read $0.125
- Verified price
- Input $0.875 / Output $7.00 / Cache read $0.0875
- Discount
- -30%
Cache read
- Official price
- $0.125
- Verified price
- $0.0875
- Discount
- -30%
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.01/search
- Verified price
- $0.007/search
- Discount
- -30%
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Default spec | Input $1.25 / Output $10.00 / Cache read $0.125 | Input $0.875 / Output $7.00 / Cache read $0.0875 | -30% |
| Prompt cache pricing | |||
| Cache read | $0.125 | $0.0875 | -30% |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.01/search | $0.007/search | -30% |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open GPT-5.1 in Console with a prompt ready to edit or send.
Help me try gpt-5.1 with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Best for- Vision
Latency-sensitive agents
Run at no reasoning for quick tool calls, then raise effort only on steps that need planning.
Code generation
Write new functions and revise existing ones from a description, and raise the effort level when debugging a stubborn failure.
Support automation
Look up account data through functions and answer in a consistent structured format.
Document Q&A
Answer questions about uploaded files and images by combining file search with the model's own reasoning over what it finds.
Prompt examples
Fix this failing integration test. Think it through only if the cause is not obvious.
Answer this customer question using the attached policy file and quote the clause you used.
Turn this meeting transcript into a JSON list of tasks with owner and due date.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is OpenAI's GPT-5.1 model?
GPT-5.1 is the OpenAI model that followed GPT-5. It targets coding and agentic work and lets you choose between reasoning and non-reasoning behavior through the effort setting.
What does the none reasoning effort do on GPT-5.1?
It runs the model without a reasoning phase for faster, cheaper turns. Raise the setting to low, medium, or high when answers need step-by-step thinking before they are returned.
Does GPT-5.1 support image input?
Yes. Text and images are accepted in the same request, and the model answers in text. It cannot generate or edit images, so pair it with an image model for that.
How is GPT-5.1 different from GPT-5?
GPT-5.1 adds a none effort level and is positioned as a flagship for coding and agents, while GPT-5 offers minimal as its lowest level. Both share a September 2024 knowledge cutoff.
Should I move from GPT-5.1 to GPT-5.2?
GPT-5.2 has a later knowledge cutoff and an xhigh effort level. Test your own prompts on it before switching, since behavior at each effort level can differ.
How much does GPT-5.1 cost?
On TokenLab, GPT-5.1 costs Input $0.875 / Output $7.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of GPT-5.1?
GPT-5.1 accepts up to 409,600 tokens of context and returns up to 128,000 tokens in one response.
Which endpoint should GPT-5.1 use?
Use https://api.tokenlab.sh/v1/responses for GPT-5.1. The request example below shows the matching code shape.
Which operations does GPT-5.1 support?
GPT-5.1 supports Text to text. Select an operation above to see its endpoint and request example.
Compare GPT-5.1
Sources
Reviewed Oct 2, 2026
More from OpenAI