OpenAI
GPT-4o mini
openai/gpt-4o-mini
Price per million tokens
- Input
- $0.150
- Output
- $0.600
- Cache write
- not offered
- Cache read
- $0.075
Passed through at the provider's list rate. Gateway adds no markup to tokens.
Limits
- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Images
- supported
What it costs to run
| Workload | Input | Output | Cost | Per 1,000 calls |
|---|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0004 | $0.45 |
| Long document summary | 50,000 | 2,000 | $0.0087 | $8.70 |
| Agent step with tools | 20,000 | 1,500 | $0.0039 | $3.90 |
| 1M in, 1M out | 1,000,000 | 1,000,000 | $0.7500 | $750.00 |
Calling it
const res = await client.chat.completions.create({
model: "openai/gpt-4o-mini",
messages: [{ role: "user", content: "Hello" }],
});