openai/gpt-5.4-mini| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| xpersona | $0.375 | $4 | 31 Jul 2026 |
| Poe | $0.68 | $4 | 31 Jul 2026 |
| vivgrid | $0.75 | $4.5 | 31 Jul 2026 |
| neon | $0.75 | $4.5 | 31 Jul 2026 |
| frogbot | $0.75 | $4.5 | 31 Jul 2026 |
| freemodel | $0.75 | $4.5 | 31 Jul 2026 |
| 302.AI | $0.75 | $4.5 | 31 Jul 2026 |
| AIHubMix | $0.75 | $4.5 | 31 Jul 2026 |
| Abacus.AI | $0.75 | $4.5 | 31 Jul 2026 |
| Azure Cognitive Services | $0.75 | $4.5 | 31 Jul 2026 |
| CrossModel | $0.75 | $4.5 | 31 Jul 2026 |
| Databricks | $0.75 | $4.5 | 31 Jul 2026 |
| DigitalOcean Gradient AI | $0.75 | $4.5 | 1 Aug 2026 |
| FastRouter | $0.75 | $4.5 | 31 Jul 2026 |
| GitHub Copilot | $0.75 | $4.5 | 31 Jul 2026 |
| Kilo Code | $0.75 | $4.5 | 31 Jul 2026 |
| LLM Gateway | $0.75 | $4.5 | 31 Jul 2026 |
| Merge Gateway | $0.75 | $4.5 | 31 Jul 2026 |
| Microsoft Foundry | $0.75 | $4.5 | 31 Jul 2026 |
| NEAR AI | $0.75 | $4.5 | 31 Jul 2026 |
| NanoGPT | $0.75 | $4.5 | 31 Jul 2026 |
| OpenAI | $0.75 | $4.5 | 31 Jul 2026 |
| OpenCode Zen | $0.75 | $4.5 | 31 Jul 2026 |
| OpenRouter | $0.75 | $4.5 | 31 Jul 2026 |
| OrcaRouter | $0.75 | $4.5 | 31 Jul 2026 |
| Pioneer | $0.75 | $4.5 | 31 Jul 2026 |
| Vercel | $0.75 | $4.5 | 31 Jul 2026 |
| ZenMux | $0.75 | $4.5 | 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 | 1,439.62 1,434–1,446 | effort: high | — |
| Arena Score in French | 1,439.35 1,424–1,455 | effort: high | — |
| Arena Score, expert questions | 1,434.04 1,425–1,443 | effort: high | — |
| Arena Score, multi-turn dialogue | 1,432.03 1,425–1,439 | effort: high | — |
| Arena Score, hard prompts | 1,425.82 1,421–1,430 | effort: high | — |
| Arena Score in Russian | 1,419.95 1,411–1,428 | effort: high | — |
| Arena Score, mathematics | 1,419.5 1,408–1,431 | effort: high | — |
| Arena Score in English | 1,412.73 1,408–1,418 | effort: high | — |
| Arena Score, overall | 1,412.71 1,409–1,417 | effort: high | — |
| Arena Score, long queries | 1,409.13 1,404–1,415 | effort: high | — |
| Arena Score, instruction following | 1,405.31 1,400–1,411 | effort: high | — |
| Arena Score in Spanish | 1,404.24 1,388–1,420 | effort: high | — |
| Arena Score, web development | 1,398.66 1,392–1,405 | effort: high | — |
| Arena Score, creative writing | 1,371.11 1,364–1,378 | effort: high | — |
| Arena Score, understanding diagrams | 1,263.79 1,255–1,273 | effort: high | — |
| Arena Score, text recognition in images | 1,255.35 1,249–1,262 | effort: high | — |
| Arena Score, working with images | 1,246.96 1,240–1,254 | effort: high | — |