GPT-5.4 is an AI model from OpenAI in the GPT series. Agent Mag tracks its context window, pricing, modalities, and supported API parameters on this page.

How do you use GPT-5.4?

GPT-5.4 can be called through OpenRouter's OpenAI-compatible API using the model ID openai/gpt-5.4. This page includes a ready-to-run curl example and the supported parameter list.

GPT-5.4 is a paid model in the OpenRouter catalog, with separate input and output token pricing shown on this page.

GPT-5.4

All models

OpenAIGPTReleased 2026-03-05

GPT-5.4

1.1M context

$2.50/M input

$15.00/M output

GPT-5.4 is OpenAI's latest model that integrates the Codex and GPT lines into a unified system. It supports a 1M+ token context window (922K input, 128K output) and handles both text and image inputs, enabling high-context reasoning, coding, and multimodal analysis. The model excels in coding, document understanding, tool use, and instruction following, making it suitable for general-purpose tasks and software engineering workflows.

What is GPT-5.4?

GPT-5.4 is an AI model from OpenAI that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare GPT-5.4 against other models for agent workflows and production deployments.

Model ID

Architecture & Specifications

Tokenizer

GPT

License

Proprietary

Released

2026-03-05

Modalities

Input

textimagefile

Output

text

Supported Parameters

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatseedstructured_outputstool_choicetools

Strengths

Supports a 1M+ token context window for high-context reasoning
Handles both text and image inputs for multimodal workflows
Excels in coding and generating production-quality code
Improved document understanding and tool use
Efficient execution of complex multi-step workflows

Limitations

Hallucination rate of 11.4% in knowledge-based tasks
Lower performance in research-level physics reasoning (23.4%)
Moderate accuracy in omniscience tasks (50.0%)
Structured output error rate of 7.16%
Tool call error rate of 0.68%

Recommended Use Cases

Software engineering and coding tasks

Document understanding and synthesis across multiple sources

Multimodal analysis combining text and image inputs

Instruction following for complex workflows

High-context reasoning in academia, finance, health, and legal domains

More from OpenAI

GPT-5.4 Image 2

272K ctx$8.00/M

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

GPT-5.4 Nano

400K ctx$0.200/M

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

GPT-5.4 Mini

400K ctx$0.750/M

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

GPT-5.4 Pro

1.1M ctx$30.00/M

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

Stay in the know

GPT-5.4

What is GPT-5.4?

More from OpenAI

Related content