OpenAI · Model
GPT-5.4 Mini pricing, context window and specs
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens, and reads up to 400,000 tokens per request. By blended price it is number 4 of OpenAI’s 10 current models here, counting from the cheapest.
- Input / 1M
- $0.75
- Output / 1M
- $4.50
- Cached / 1M
- $0.075
- Context
- 400,000
- Max output
- 128,000
- Released
- 2026-03-17
Estimate your cost with GPT-5.4 MiniCompare all OpenAI modelsCount tokens for GPT-5.4 Mini
Pricing
GPT-5.4 Mini API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.75 | $4.50 |
| Cached input (read) | $0.075 | – |
| Batch API | $0.375 | $2.25 |
Output costs 6.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price.
Examples
What GPT-5.4 Mini costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00242 | $73.57 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00594 | $90.34 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0174 | $105.85 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.00435 | $39.69 |
Change any number in the cost calculator.
Context
Context window
GPT-5.4 Mini accepts up to 400,000 tokens per request, roughly 300,000 English words or 600 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 128,000 tokens.
Filling the whole window with one prompt costs about $0.30 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- file, image, text
- Knowledge cutoff
- 2025-08-31
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
GPT-5.4 Mini model ID
- OpenRouter
openai/gpt-5.4-mini- OpenAI API
gpt-5.4-mini(alias)gpt-5.4-mini-2026-03-17(pinned)
OpenAI lists GPT-5.4 Mini as current. Every GPT model ID, with aliases and snapshots.
OpenAI
Where GPT-5.4 Mini sits in OpenAI’s line-up
Ranked by blended price (three parts input to one part output, $1.6875 per 1M for GPT-5.4 Mini), it is number 4 of OpenAI’s 10 current models here, counting from the cheapest. One step down, GPT-4o-mini costs $0.2625 blended (84% less). Unlike GPT-5.4 Mini, it reads up to 128,000 tokens (400,000 here), caps a reply at 16,384 tokens (128,000 here) and has no reasoning mode. One step up, GPT-6.1 Sol costs $4 (2.4× as much). Unlike GPT-5.4 Mini, it reads up to 1,050,000 tokens (400,000 here). See every OpenAI model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| gpt-oss-120b | $0.037 | $0.17 | 131,072 | 2025-08-05 |
| GPT-6 Luna | $0.10 | $0.50 | 1,050,000 | 2026-09-22 |
| GPT-4o-mini | $0.15 | $0.60 | 128,000 | 2024-07-18 |
| GPT-5.4 Mini (this page) | $0.75 | $4.50 | 400,000 | 2026-03-17 |
| GPT-6.1 Sol | $2 | $10 | 1,050,000 | 2026-09-29 |
| GPT-4o | $2.50 | $10 | 128,000 | 2024-05-13 |
| GPT-5.6 Terra | $2 | $12 | 1,050,000 | 2026-07-09 |
| GPT-5.5 | $5 | $30 | 1,050,000 | 2026-04-24 |
| GPT-6 Astra | $10 | $50 | 1,050,000 | 2026-09-04 |
| GPT-5.5 Pro | $30 | $180 | 1,050,000 | 2026-04-24 |
OpenAI’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Earlier versions of GPT-5.4 Mini
The previous model in this line is GPT-5 Mini, first listed on 2025-08-07. Compared with it, GPT-5.4 Mini’s input price is 200% higher and its output price is 125% higher.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GPT-5 Mini | $0.25 | $2 | 400,000 | 2025-08-07 |
| GPT-4.1 Mini | $0.40 | $1.60 | 1,047,576 | 2025-04-14 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
Cheaper alternatives
- Seed-2.0-MiniByteDance Seed90% cheaper
- GPT-6 LunaOpenAI88% cheaper
- Claude Haiku 5.5Anthropic88% cheaper
- Qwen3.8 Omni FlashQwen86% cheaper
- GLM 4.6VZ.ai73% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Gemini 3.8 FlashGoogle$0.75 / $3.75
- GLM 5V TurboZ.ai$1.20 / $4
- DeepSeek V4 Pro 0813DeepSeek$1.32 / $3.96
- Muse Spark 1.3Meta$1.25 / $4.25
- Kimi K2.7 CodeMoonshot AI$0.6712 / $3.35
Current models from other major providers, closest blended price.
FAQ
GPT-5.4 Mini questions
How much does GPT-5.4 Mini cost?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens, with cached input at $0.075. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00292. Use the LLM cost calculator for your own workload.
What is GPT-5.4 Mini’s context window?
400,000 tokens, about 300,000 English words or 600 printed pages, shared between your prompt and the reply. A single reply can be up to 128,000 tokens.
Does GPT-5.4 Mini support prompt caching and batch requests?
Yes, cached input is billed at $0.075 per million tokens (10% of the normal input price). A batch API is available at $0.375 input and $2.25 output per million tokens.
What are cheaper alternatives to GPT-5.4 Mini?
With the same essentials (image input and tool calling), the cheapest options are Seed-2.0-Mini (90% cheaper), GPT-6 Luna (88% cheaper), Claude Haiku 5.5 (88% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for GPT-5.4 Mini?
On OpenRouter it is openai/gpt-5.4-mini. In OpenAI’s own API, use gpt-5.4-mini; OpenAI lists the model as current. The GPT model ID list has every alias and snapshot. Pass the ID as the model value in each request.
What did GPT-5.4 Mini replace?
The previous OpenAI model in the same line is GPT-5 Mini, first listed on 2025-08-07. Compared with it, GPT-5.4 Mini’s input price is 200% higher and its output price is 125% higher. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is GPT-5.4 Mini open source?
No, GPT-5.4 Mini is only available through OpenAI’s API and partners; its weights aren’t published.