Model detail
GPT-5.4 20260305
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
- Model ID
-
gpt-5.4-2026-03-05
- Context length
- 1.05M
- Max output
- 128K
- I/O modalities
- 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?
1M+ context window with text and image inputs
Use gpt-5.4-2026-03-05 for high-context reasoning, coding, and multimodal analysis. It unifies the Codex and GPT lines with a 922K input, 128K output context window.
What should you check before using it?
Confirm the snapshot date matches your stability needs
This is the 2026-03-05 snapshot of GPT-5.4. Verify that this version provides the stability you need. Test coding, document understanding, and multi-step workflows. Knowledge cutoff: 2025-08-31.
Why use it through MixRoute?
Swap the base URL, keep the GPT-5.4 client
MixRoute serves GPT-5.4 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-5.4-2026-03-05 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
GPT-5.4 supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
GPT-5.4 can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
GPT-5.4 supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
GPT-5.4 supports prompt caching under supported routing conditions.
Vision input
GPT-5.4 can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call GPT-5.4 through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
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
Compare gpt-5.4-2026-03-05 against models of similar capability and pricing on your actual workload. Evaluate latency, output quality, instruction following, and cost per task. Run side-by-side tests with your own prompts — the best model depends on your specific use case, not just benchmark scores.
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.