openai/gpt-4o-2024-11-20| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| Abacus.AI | $2.5 | $10 | 31 Jul 2026 |
| Kilo Code | $2.5 | $10 | 31 Jul 2026 |
| Merge Gateway | $2.5 | $10 | 31 Jul 2026 |
Microsoft Foundry
azure/global-standard/gpt-4o-2024-11-20
|
$2.5 | $10 | 31 Jul 2026 |
| NanoGPT | $2.5 | $10 | 31 Jul 2026 |
| OpenAI | $2.5 | $10 | 31 Jul 2026 |
| OpenRouter | $2.5 | $10 | 31 Jul 2026 |
| OrcaRouter | $2.5 | $10 | 31 Jul 2026 |
Microsoft Foundry
azure/eu/gpt-4o-2024-11-20
|
$2.75 | $11 | 31 Jul 2026 |
| Venice AI | $3.125 | $12.5 | 1 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.
A single provider appears several times if it sells this model under different identifiers and at different prices — for example, at different weight precision. The identifier is shown next to the name. Identical offers that arrived from two sources under different spellings are merged into one row.
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 |
|---|---|---|---|
| Creative writing (Lech Mazur’s evaluation) | 81.8 % | — | lechmazur/writing Github repository |
| GeoBench — locating a place from a photograph | 71 % | — | GeoBench leaderboard |
| MATH, difficulty level five | 49.77 % | · with a tuned harness | Epoch evaluations |
| SWE-bench Verified — fixing bugs in repositories | 30.99 % | · with a tuned harness | Epoch evaluations |
| GPQA Diamond — graduate-level questions | 30.51 % | · with a tuned harness | Epoch evaluations |
| WeirdML — unusual machine learning tasks | 25.12 % | — | WeirdML Leaderboard |
| Aider Polyglot — code edits in six languages | 18.2 % | · with a tuned harness | Aider LLM Leaderboards |
| Cybench — cybersecurity tasks | 12.5 % | · with a tuned harness | Cybench leaderboard |
| GDPval — tasks from real occupations | 9.9 % | — | — |
| The Agent Company — work tasks in an office environment | 8.6 % | — | TheAgentCompany experiment results github |
| Mock AIME 2024–2025 — olympiad problems | 6.16 % | · with a tuned harness | Epoch evaluations |
| ARC-AGI — generalising to unseen patterns | 4.5 % | · with a tuned harness | ARC Prize Leaderboard |
| APEX-Agents | 1.1 % | — | — |
| GSO-Bench — code optimisation | 0 % | — | GSO Leaderboard |
| Humanity’s Last Exam — expert-level questions | 0 % | — | — |
| CritPt — physics problems | 0 % | — | — |
| ARC-AGI-2 | 0 % | — | — |