Model detail
gpt-5.4
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.
Model specs
- Context length
- 1.05M
- Max output
- 128K
- I/O modalities
- Text / Image
- Released
- 2026-03
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /1M Tokens
| Tier | Input /1M Tokens | Output /1M Tokens | Cache read /1M Tokens |
|---|---|---|---|
| standard Length ≤ 272K | $2.5000 | $15.0000 | $0.2500 |
| long_context Length > 272K | $5.0000 | $22.5000 | $0.5000 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Frontier general-purpose reasoning and software engineering
Use gpt-5.4 for complex analysis, coding, document understanding, and multi-step workflows where one capable default model is useful.
What should you check before using it?
Validate long-context and multimodal behavior on your workload
Test representative text and image inputs, long documents, tool calls, latency, and current pricing before moving production traffic.
How should you start?
Begin with the stable gpt-5.4 model ID
Use model ID gpt-5.4 in an existing compatible integration, then compare results against your current model on the same evaluation set.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
gpt-5.4 is a frontier general-purpose model for complex reasoning, coding, document understanding, tool use, and multi-step workflows. It is intended to serve as a capable default when one model must cover varied professional tasks.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.