GPT-5.1-Codex-Max pricing.
Prices checked
GPT-5.1-Codex-Max costs $1.25 in and $10 out per million tokens from OpenRouter; the cheapest price is $3.08 at Poe, checked .
OpenRouter's own price
OpenRouter
$1.25 in · $10 out
290% above the typical price of the 392 text models we track.
Cheapest price
Poe
$1.10 in · $9 out
11% less than OpenRouter, and the provider says why.
Web search from this model costs $10 per 1,000 searches, plus its tokens; dedicated search APIs from $1
Every provider selling GPT-5.1-Codex-Max
- 1
$1.10 in · $9 out
$3.08/M tokens - 2
$1.19 in · $9.50 out
$3.27/M tokens - 3
$1.25 in · $10 out
$3.44/M tokens - 4
Vivgrid
Same as maker$1.25 in · $10 out
$3.44/M tokens - 5
$1.25 in · $10 out
$3.44/M tokens - 6
$1.25 in · $10 out
$3.44/M tokens - 7
$1.25 in · $10 out
$3.44/M tokens - 8
$1.25 in · $10 out
$3.44/M tokens - 9
$1.25 in · $10 out
$3.44/M tokens - 10
$1.25 in · $10 out
$3.44/M tokens - 11
$1.25 in · $10 out · 256k context here
$3.44/M tokens - 12
$1.25 in · $10 out · 272k context here
$3.44/M tokens - 13
$1.25 in · $10 out
$3.44/M tokens - 14
$2.50 in · $20 out
$6.88/M tokens - 15Costs more
$2.65 in · $21.16 out
$7.27/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at Poe, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. OpenAI trained GPT-5.1-Codex-Max and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- Credits
- Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
Similar models
Models from other labs that do what GPT-5.1-Codex-Max does, cheapest first. Each percentage is against GPT-5.1-Codex-Max's cheapest price, $3.08 per M tokens.
Frequently asked
- Who sells GPT-5.1-Codex-Max cheapest?
- Poe, at $1.10 in and $9 out per million tokens, checked 31 Oct 2026. Priced in credits or points that convert to dollars, so the rate moves when the conversion does.
- Is GPT-5.1-Codex-Max open weights?
- No. OpenAI keeps the weights, so every price on this page is OpenAI's own or a resale of it. A price below OpenAI's here needs a published reason, or it is listed and not ranked.
- How much context does GPT-5.1-Codex-Max hold?
- 400,000 tokens in one call, which is about 400k, and it can call your own functions.
- How does GPT-5.1-Codex-Max compare with the rest of the market?
- At $3.44 per million tokens, OpenRouter's own price is 290% above the typical $0.88 across the 392 text models we track.
More from OpenAI