Compare
Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.
Monthly bill
Token models use the token counts. Other models use units times the flat rate.
Lowest bill: Arize AI Qwen 2 1.5B Instruct · $0.20
Add another
Search by name, then add up to four.
| OpenAI: GPT-5.6 Luna (batch) | Arize AI Qwen 2 1.5B Instruct | |
|---|---|---|
| Provider | OpenAI | Together |
| Modality | text, image | text |
| Context | 1.1M | 33K |
| Input | $0.1/1M | $0.1/1M |
| Output | $0.6/1M | $0.1/1M |
| Cache read | $0.01/1M | Not published— |
Tiers and extras
- OpenAI: GPT-5.6 Luna (batch)
- Web search: $0.01 per request; Above 272,000 prompt tokens: in $0.2 · out $0.9 · cache read $0.02
- Arize AI Qwen 2 1.5B Instruct
- —