OpenAI: GPT-5.4 Pro
gpt-5.4-pro- Input / Output
- $30.00 / $180.00
- Context
- 1.05M
- Max output
- 128K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt CacheReasoning
About GPT-5.4 Pro
GPT-5.4 Pro is the higher-compute tier of GPT-5.4. OpenAI says it produces smarter and more precise responses by using more compute. It keeps the large context window, accepts text and images, supports computer use, and runs at medium, high, or xhigh effort. Requests may take minutes.
Where it works well
- Uses additional compute for more precise answers than standard GPT-5.4.
- Medium, high, or xhigh effort, with medium as the default.
- Supports computer use, web search, file search, and MCP.
- Handles very long inputs thanks to the same large window as GPT-5.4.
When to choose another model
- Responses are slow, so interactive use belongs on standard GPT-5.4.
- There is no none or low effort, so quick turns go to GPT-5.4.
- It does not return structured JSON on a schema, so strict-format jobs fit GPT-5.4 better.
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-5.4-pro", "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.
Input tokens <= 272K
per 1M tokens- Official price
- Input $30.00 / Output $180.00
- Verified price
- —
- Discount
- —
Input tokens 272K-1.05M
per 1M tokens- Official price
- Input $60.00 / Output $270.00
- Verified price
- —
- Discount
- —
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.01/search
- Verified price
- —
- Discount
- —
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input tokens <= 272K | Input $30.00 / Output $180.00 | — | — |
| Input tokens 272K-1.05M | Input $60.00 / Output $270.00 | — | — |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.01/search | — | — |
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-5.4 Pro in Console with a prompt ready to edit or send.
Help me try gpt-5.4-pro with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Best for- Reasoning
- Vision
Precision review
Audit long technical or legal documents where a missed clause or figure can cost real money.
Complex agent runs
Run long computer-use or tool workflows that smaller models tend to derail partway through.
Research questions
Combine several sources into a justified conclusion with the evidence for each claim.
Large code audits
Read an entire module and find subtle defects that quicker passes overlook.
Prompt examples
Audit this 80-page agreement against our policy checklist and cite each deviation.
Plan and execute this multi-system reconciliation, pausing before any destructive step.
Reconcile these three analyst reports and explain which numbers are not comparable.
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 GPT-5.4 Pro?
GPT-5.4 Pro is OpenAI's high-compute variant of GPT-5.4, built for demanding problems where the standard model's answers are not precise enough. Expect slower replies and a heavier reasoning pass on each call.
What reasoning effort does GPT-5.4 Pro use?
Medium by default, with high and xhigh available. There is no none or low setting, so every request includes a real reasoning phase. Pick the level that your own evaluation shows is worth the added wait.
Can I call GPT-5.4 Pro like other chat models?
Yes. It is called with the same OpenAI-style request fields as other chat models, including images and function calling. Because answers can take minutes, set generous client timeouts and handle long jobs asynchronously.
Why might GPT-5.4 Pro time out?
Complex requests may take several minutes to finish. Raise client timeouts, or stream the response, so that a dropped connection does not lose the result.
When is GPT-5.4 Pro better than GPT-5.4?
Use it when the standard model's answers are not precise enough and you can wait. For interactive or high-volume work GPT-5.4 is the faster, more practical choice.
How much does GPT-5.4 Pro cost?
On TokenLab, GPT-5.4 Pro costs Input $30.00 / Output $180.00 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-5.4 Pro?
GPT-5.4 Pro accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens in one response.
Which endpoint should GPT-5.4 Pro use?
Use https://api.tokenlab.sh/v1/responses for GPT-5.4 Pro. The request example below shows the matching code shape.
Which operations does GPT-5.4 Pro support?
GPT-5.4 Pro supports Text to text. Select an operation above to see its endpoint and request example.
Compare GPT-5.4 Pro
Sources
Reviewed Oct 2, 2026
More from OpenAI