GPT-5.4 Image 2
GPTSpecialized
ThinkingVisionStructured Output
About this model
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...
Performance Tier
Specialized
GPT-5.4 Image 2 is a specialized model from GPT : built for a specific domain.
Domain-specific model. Optimized for a particular task such as code generation, image creation, or web search.
Pricing
This model is included in Elosia plansHigh
High pricing. Reserve this level for tasks that demand maximum quality.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $8.00 |
| Output (completion) | $15.00 |
| Cache read | $2.00 |
Capabilities
Context Length272K
Max Output Tokens128K
TokenizerGPT
Inputimage, text, file
Outputimage, text
Release DateApril 21, 2026
Recommended Use Cases
Creative WritingAnalysis
Strengths
- Combines GPT-5.4 reasoning with GPT Image 2 generation in a single model
- Seamless text + image workflows — reason, code and create visuals in one session
- 272K-token context window for long multimodal prompts
- Native computer-use and tool support inherited from GPT-5.4
Limitations
- Premium pricing ($8/M input, $15/M output)
- Images billed as output tokens in addition to text output
- Multimodal variant without dedicated text-reasoning benchmarks — use base GPT-5.4 for pure text tasks
Resources
This model may use your data for training