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: OpenAI: GPT-6 Sol Pro (batch) · $6.00
Add another
Search by name, then add up to four.
| OpenAI: GPT-6 Sol Pro (batch) | Anthropic: Claude Sonnet 5 (batch) | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Modality | text, image | text, image |
| Context | 1.1M | 1M |
| Input | $1/1M | $1/1M |
| Output | $5/1M | $5/1M |
| Cache read | $0.1/1M | $0.1/1M |
| Cache write | $1.25/1M | $1.25/1M |
| 1-hour cache write | Not published— | $2/1M |
Tiers and extras
- OpenAI: GPT-6 Sol Pro (batch)
- Web search: $0.01 per request; Above 272,000 prompt tokens: in $2 · out $7.5 · cache read $0.2 · cache write $2.5
- Anthropic: Claude Sonnet 5 (batch)
- Web search: $0.01 per request