gpt-5.1-codex-max API price comparison
Compare gpt-5.1-codex-max token prices across supported API token platforms.
Cheapest overall
Micu
0.59 USD/M tokens combined per 1M tokens
Lowest input
Micu
0.07 USD/M tokens input per 1M tokens
Lowest output
Micu
0.52 USD/M tokens output per 1M tokens
Last refreshed
Jun 20, 2026
5 listed platforms
Best listed option
gpt-5.1-codex-max is currently cheapest overall on Micu, with input at 0.07 USD/M tokens and output at 0.52 USD/M tokens per million tokens.
Pricing insight
Across 5 listed routes, gpt-5.1-codex-max is cheapest overall on Micu at 0.59 USD/M tokens. The median combined price is 6.75 USD/M tokens, so the cheapest route is about 91% below the median listed route.
-
Lowest total cost
Micu
Best first check for balanced coding-agent sessions: 0.59 USD/M tokens.
-
Prompt-heavy work
Micu
Useful for large repositories and long context reads: 0.07 USD/M tokens input.
-
Response-heavy work
Micu
Useful for long answers, edits, and agent loops: 0.52 USD/M tokens output.
Median combined price
6.75 USD/M tokens
Baseline for judging whether the cheapest route is unusually low.
Cache price coverage
80%
4 of 5 routes publish cache read or write prices.
Fresh rows
0/5
Routes crawled in the last 72 hours.
Use case fit
gpt-5.1-codex-max is useful for coding agent runs, repository edits, and review workflows where output tokens can grow quickly. Compare total input plus output cost before routing sustained Codex workloads.
Platform price comparison
| Platform | Ratio | Input | Output | Total |
|---|---|---|---|---|
| Micu | 0.05x | 0.07 USD/M tokens | 0.52 USD/M tokens | 0.59 USD/M tokens |
| ZetaTechs | 0.30x | 0.37 USD/M tokens | 2.96 USD/M tokens | 3.33 USD/M tokens |
| Yunwu | 0.60x | 0.75 USD/M tokens | 6.00 USD/M tokens | 6.75 USD/M tokens |
| Atlas Cloud | 1.00x | 1.25 USD/M tokens | 10.00 USD/M tokens | 11.25 USD/M tokens |
| Crazyrouter | 1.00x | 1.25 USD/M tokens | 10.00 USD/M tokens | 11.25 USD/M tokens |
FAQ
Where is gpt-5.1-codex-max cheapest?
Micu has the lowest listed combined price at 0.59 USD/M tokens per 1M tokens.
What do input and output prices mean?
Input is charged for prompt tokens you send. Output is charged for tokens generated by the model.
How often are prices refreshed?
Prices are crawler-backed and this page was last refreshed Jun 20, 2026. Always confirm before large purchases.