GPT-4o mini pricing
The model that made per-token cost stop mattering for most simple tasks, and the benchmark every subsequent cheap model has been priced against.
List prices checked
By OpenAI · Small / fast tier
Token pricing
Per million tokens, from the official price list.
| Token type | Price per 1M | Notes |
|---|---|---|
| Input | $0.150 | Everything you send, including the system prompt |
| Output | $0.600 | Everything the model generates, reasoning tokens included |
| Cached input | $0.075 | Repeated prefixes served from cache |
| Blended (3:1) | $0.262 | One number for ranking, at three input tokens per output token |
Source: OpenAI pricing (May 2026). Published list prices only — committed-use discounts, regional variation, and per-request charges are not included. Not yet independently re-checked against the vendor’s page.
Capabilities
| Property | Value |
|---|---|
| Context window | 128K tokens |
| Max output | 16K tokens |
| Inputs accepted | text, image |
| Cost to fill the context once | $0.02 |
What it costs per month
Token prices applied to three workload shapes. Input-heavy and output-heavy workloads rank models very differently.
In-app chat assistant
A support or help assistant handling a few thousand conversations a month, with short prompts and short answers.
$6.00/mo
- 20M input tokens$3.00
- 5M output tokens$3.00
- If fully cached$4.50
RAG over documents
Retrieval-augmented answering where each request stuffs several retrieved passages into the prompt, so input dominates.
$54/mo
- 300M input tokens$45
- 15M output tokens$9.00
- If fully cached$32
Coding agent
An agentic loop that reads files and writes patches, generating heavy output and re-sending large context on every turn.
$120/mo
- 400M input tokens$60
- 100M output tokens$60
- If fully cached$90
GPT-4o mini vs other small / fast models
Same capability tier, ranked by blended token price.
| Model | Input | Output | Context | Compare |
|---|---|---|---|---|
| Cohere Command R | $0.150 | $0.600 | 128K | Head to head |
| Gemini 2.5 Flash-Lite | $0.100 | $0.400 | 1M | Head to head |
| Mistral Small | $0.100 | $0.300 | 131K | Head to head |
| GPT-5 nano | $0.050 | $0.400 | 400K | Head to head |
| GPT-4.1 mini | $0.400 | $1.60 | 1M | Head to head |
Questions about pricing
- How much does the GPT-4o mini API cost in 2026?
- $0.150 per million input tokens and $0.600 per million output tokens, from OpenAI's published pricing. The table above converts that into a monthly figure for three common workloads.
- What is the GPT-4o mini context window?
- 128K tokens, with up to 16K tokens of output per request. Filling the window costs whatever that many input tokens cost — at $0.150 per million, a single full-context request runs about $0.02.
- Does GPT-4o mini support prompt caching?
- Yes. Cached input is billed at $0.075 per million tokens, roughly 2× cheaper than uncached input. For an agent that resends the same system prompt and file context on every turn, that discount usually matters more than the headline rate does.
- Is GPT-4o mini cheaper than the alternatives?
- On a blended 3:1 input-to-output basis it works out at $0.262 per million tokens. The comparison table below ranks it against the other small / fast models in the dataset, and the head-to-head pages model both against identical workloads.