OpenAI
gpt-5-codex:batch
openai/gpt-5-codex:batch
Price per million tokens
- Input
- $0.791
- Output
- $6.330
- Cache write
- not offered
- Cache read
- $0.079
What you pay. It is what the tokens cost us to buy plus 20%, and your usage page shows what we paid beside what you paid on every request you send.
Limits
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- Images
- supported
What it costs to run
| Workload | Input | Output | Cost | Per 1,000 calls |
|---|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0040 | $3.96 |
| Long document summary | 50,000 | 2,000 | $0.0522 | $52.22 |
| Agent step with tools | 20,000 | 1,500 | $0.0253 | $25.32 |
| 1M in, 1M out | 1,000,000 | 1,000,000 | $7.1212 | $7121.25 |
Calling it
const res = await client.chat.completions.create({ model: "openai/gpt-5-codex:batch", messages: [{ role: "user", content: "Hello" }], });