openai/gpt-5.3-codex| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| Poe | $1.6 | $13 | 31 Jul 2026 |
| vivgrid | $1.75 | $14 | 31 Jul 2026 |
| neon | $1.75 | $14 | 31 Jul 2026 |
| frogbot | $1.75 | $14 | 31 Jul 2026 |
| freemodel | $1.75 | $14 | 31 Jul 2026 |
| AIHubMix | $1.75 | $14 | 31 Jul 2026 |
| Abacus.AI | $1.75 | $14 | 31 Jul 2026 |
| Azure Cognitive Services | $1.75 | $14 | 31 Jul 2026 |
| Cloudflare AI Gateway | $1.75 | $14 | 31 Jul 2026 |
| DigitalOcean Gradient AI | $1.75 | $14 | 1 Aug 2026 |
| FastRouter | $1.75 | $14 | 31 Jul 2026 |
| GitHub Copilot | $1.75 | $14 | 31 Jul 2026 |
| Kilo Code | $1.75 | $14 | 31 Jul 2026 |
| LLM Gateway | $1.75 | $14 | 31 Jul 2026 |
| Microsoft Foundry | $1.75 | $14 | 31 Jul 2026 |
| NanoGPT | $1.75 | $14 | 31 Jul 2026 |
| OpenAI | $1.75 | $14 | 31 Jul 2026 |
| OpenCode Zen | $1.75 | $14 | 31 Jul 2026 |
| OpenRouter | $1.75 | $14 | 31 Jul 2026 |
| OrcaRouter | $1.75 | $14 | 31 Jul 2026 |
| Pioneer | $1.75 | $14 | 31 Jul 2026 |
| Requesty | $1.75 | $14 | 31 Jul 2026 |
| Vercel | $1.75 | $14 | 31 Jul 2026 |
| ZenMux | $1.75 | $14 | 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, web development | 1,408.9 1,395–1,423 | — | — |
| WeirdML — unusual machine learning tasks | 79.3 % | — | WeirdML Leaderboard |
| Terminal-Bench — working in the command line | 78.4 % | · with a tuned harness | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| SWE-bench Verified — fixing bugs in repositories | 74.79 % | effort: high · with a tuned harness | Epoch evaluations |
| APEX-Agents | 31.8 % | — | — |