gemini-3.5-flash-lite| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| CrossModel | $0.3 | $2.5 | 2 Aug 2026 |
| Google DeepMind | $0.3 | $2.5 | 31 Jul 2026 |
| Google Vertex AI | $0.3 | $2.5 | 31 Jul 2026 |
| LLM Gateway | $0.3 | $2.5 | 31 Jul 2026 |
| OpenCode Zen | $0.3 | $2.5 | 31 Jul 2026 |
| OpenRouter | $0.3 | $2.5 | 31 Jul 2026 |
| Vercel | $0.3 | $2.5 | 31 Jul 2026 |
| Venice AI | $0.375 | $3.125 | 31 Jul 2026 |
Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.
The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score, programming | 1,455.6 1,441–1,470 | — | — |
| Arena Score in French | 1,453.97 1,412–1,496 | — | — |
| Arena Score, web development | 1,451.88 1,408–1,496 | — | — |
| Arena Score, multi-turn dialogue | 1,445.05 1,426–1,464 | — | — |
| Arena Score, hard prompts | 1,441.84 1,432–1,451 | — | — |
| Arena Score in Russian | 1,440.42 1,416–1,464 | — | — |
| Arena Score, overall | 1,438.61 1,431–1,446 | — | — |
| Arena Score, long queries | 1,437.38 1,426–1,449 | — | — |
| Arena Score, expert questions | 1,435.08 1,411–1,460 | — | — |
| Arena Score in English | 1,433.44 1,421–1,446 | — | — |
| Arena Score, creative writing | 1,420.66 1,403–1,439 | — | — |
| Arena Score, instruction following | 1,415.12 1,402–1,429 | — | — |
| Arena Score, mathematics | 1,414.68 1,378–1,451 | — | — |
| Arena Score, working with images | 1,256.63 1,220–1,294 | — | — |
| Arena Score, agent tasks | -0.1 0–0 | — | — |