GPT-5.4 delivers powerful reasoning, coding, and professional knowledge work. Supports multimodal inputs (text and image) with adjustable reasoning depth. Token-based pricing: $1.25/M input tokens, $9.00/M output tokens. Two endpoints: standard async (/gpt-5-4) and live streaming (/gpt-5-4/stream) via SSE.
About this model
GPT-5.4 is OpenAI's latest flagship model delivering powerful reasoning, coding, and professional knowledge work. Supports multimodal inputs (text and image) and adjustable reasoning depth. Token-based pricing: $1.25 per million input tokens and $9.00 per million output tokens — well below official OpenAI pricing.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $1.25/M input tokens, $9.00/M output tokens | Token-based billing. Minimum $0.00023 per call. ~71% of official input pricing, ~64% of official output pricing. Supports Prompt Caching (0.1x for hits, 1.25x for creation). |
| OpenAI (official) | ~$1.75/M input tokens, ~$14.00/M output tokens | Official pricing via api.openai.com. |
| Fal.ai | Not available | GPT-5.4 is not available on Fal.ai. |
Token-based billing. Minimum $0.00023 per call. ~71% of official input pricing, ~64% of official output pricing. Supports Prompt Caching (0.1x for hits, 1.25x for creation).
Official pricing via api.openai.com.
GPT-5.4 is not available on Fal.ai.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | The user message or instruction. | Write a Python function to parse nested JSON with error handling. |
| Image URL | string | Optional image URL for multimodal requests. | undefined |
The user message or instruction.
Write a Python function to parse nested JSON with error handling.Optional image URL for multimodal requests.
undefinedDeveloper documentation
POST /api/v1/gpt-5-4 — returns request_id, poll for result via /api/v1/predictions/{id}/result.
POST /api/v1/gpt-5-4/stream — returns a live SSE stream. Each chunk: data: {"choices":[{"delta":{"content":"text"}}]}, ending with data: [DONE].
See Streaming Documentation for full code examples.
Frequently asked
Pricing is token-based: $1.25 per million input tokens and $9.00 per million output tokens. The minimum charge per call is $0.00023. Actual cost is deducted after each call based on token counts returned by the model.
/gpt-5-4 is async — you receive a request_id and poll for the result. /gpt-5-4/stream returns a live SSE stream. Use streaming for chat UIs; use the async endpoint for workflows and automation.
Yes. Pass an image_url in the request body to include an image as multimodal input alongside your text prompt.
Yes. Prompt Caching allows you to reuse frequently used text prompts at reduced rates. Cache hits (reusing previously cached tokens) are charged at 0.1x of the input cost. New cache creation (writing new tokens to cache for future reuse) is charged at 1.25x of the standard input cost.