Back to Models
GPT-5.4 Image 2
It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...
4/21/2026
272,000 tokens
Specifications
Modalities
Input
image
text
file
Output
image
text
Supported Parameters
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
presence_penalty
reasoning
reasoning_effort
response_format
seed
stop
structured_outputs
top_logprobs
Max Output Tokens
128,000Reasoning Configuration
- Default
- Thinking off
- Selectable effort levels
- xhighhighmediumlownone
- Turning thinking off
- Possible (reasoning.enabled: false)
Data policy
- Prompt retention
- Unknown — we could not confirm
- Training
- Unknown — not declared
"Unknown" does not mean "safe". It means we could not confirm it.
Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.
Frequently asked questions
- Is GPT-5.4 Image 2 available on FastMetal?
- Not at the moment. GPT-6.1 Sol, from the same lab, is available on the FastMetal API today.
- What is the context window of GPT-5.4 Image 2?
- 272,000 tokens, shared between the prompt and the response.