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: Meta Llama 3.1 70B Instruct Turbo · $1.76
Add another
Search by name, then add up to four.
| Meta Llama 3.1 70B Instruct Turbo | OpenAI: GPT-5.2 (batch) | |
|---|---|---|
| Provider | Together | OpenAI |
| Modality | text | text, image |
| Context | 131K | 400K |
| Input | $0.88/1M | $0.875/1M |
| Output | $0.88/1M | $7/1M |
| Cache read | Not published— | $0.0875/1M |
Tiers and extras
- Meta Llama 3.1 70B Instruct Turbo
- —
- OpenAI: GPT-5.2 (batch)
- Web search: $0.01 per request