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: gpt 4.1 cached Inp glbl · $10.80
Add another
Search by name, then add up to four.
| gpt 4.1 cached Inp glbl | Anthropic: Claude Sonnet Latest | |
|---|---|---|
| Provider | Azure | Anthropic |
| Modality | text | text, image |
| Context | — | 1M |
| Input | $2/1M | $2/1M |
| Output | $8.8/1M | $10/1M |
| Cache read | $0.5/1M | $0.1/1M |
| Cache write | Not published— | $2.5/1M |
| 1-hour cache write | Not published— | $4/1M |
Tiers and extras
- gpt 4.1 cached Inp glbl
- —
- Anthropic: Claude Sonnet Latest
- Web search: $0.01 per request