databricks/databricks-llama-2-70b-chat| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| Databricks | $0.5 | $1.5 | 31 Jul 2026 |
| Replicate | $0.65 | $2.75 | 31 Jul 2026 |
| Perplexity | $0.7 | $2.8 | 31 Jul 2026 |
| Amazon Bedrock | $1.95 | $2.56 | 2 Aug 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 in English | 1,156.13 1,150–1,163 | — | — |
| Arena Score in Spanish | 1,141.75 1,113–1,171 | — | — |
| Arena Score, overall | 1,115.39 1,110–1,121 | — | — |
| Arena Score, mathematics | 1,091.27 1,081–1,101 | — | — |
| Arena Score in French | 1,088.78 1,061–1,117 | — | — |
| Arena Score, multi-turn dialogue | 1,088.09 1,078–1,099 | — | — |
| Arena Score in Russian | 1,081.92 1,067–1,096 | — | — |
| Arena Score, programming | 1,079.26 1,069–1,089 | — | — |
| Arena Score, creative writing | 1,075.28 1,065–1,085 | — | — |
| Arena Score, hard prompts | 1,073.32 1,065–1,081 | — | — |
| Arena Score, instruction following | 1,071.32 1,064–1,079 | — | — |
| Arena Score, long queries | 1,062.29 1,050–1,075 | — | — |
| Arena Score, expert questions | 1,038.83 1,022–1,056 | — | — |