Model pricing
Rates are USD per 1M tokens. Pricing is optional: a model with no entry here still runs, the PR comment simply appears without a cost estimate, and bot/scripts/deploy.py reports it as a warning rather than blocking the deploy.
| Provider | Model | In | Out | Verified | Source |
|---|---|---|---|---|---|
gemini |
gemini-flash-latest |
0.30 | 2.50 | 2026-07-23 | source |
groq |
llama-3.3-70b-versatile |
0.59 | 0.79 | 2026-07-23 | source |
vertex |
gemini-2.5-flash |
0.30 | 2.50 | 2026-08-14 | source |
vertex |
gemini-flash-latest |
0.30 | 2.50 | 2026-07-23 † | source |
† vertex/gemini-flash-latest: inherited from the gemini (AI-Studio) entry on a same-token-price rationale; not independently checked against Vertex's own pricing page