openai Vision Reasoning

GPT-5.1-Codex pricing & benchmarks

Released Nov 13, 2025 · served by 2 providers

Input / 1M tokens$1.25
Output / 1M tokens$10.00
Context window400K
Cached input$0.130
1M in + 300K out$4.25

What GPT-5.1-Codex is

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

Providers and prices for GPT-5.1-Codex

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Azurecheapest $1.25 $10.00 400K 100.0%
OpenAI $2.50 $20.00 400K 0.0%

GPT-5.1-Codex benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
mobileapps agents #17 1199 53.4%
fullstack agents #26 1086 44.5%
webapps agents #33 1073 44.1%
dataviz models #47 1202 50.7%
gamedev models #53 1195 52.3%
codecategories models #60 1181 55.2%
website models #62 1186 56%

FAQ

How much does the GPT-5.1-Codex API cost?

$1.25 per 1M input tokens and $10.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $4.25.

Is GPT-5.1-Codex free?

No. It is a paid model starting at $1.25 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GPT-5.1-Codex?

Azure at $1.25 input / $10.00 output per 1M tokens.

Can I self-host GPT-5.1-Codex?

No. GPT-5.1-Codex is closed-weight and only available through hosted APIs.