GPT-5.1-Codex is a version of GPT-5.1 optimized for software engineering and coding workflows, both in interactive sessions and in long, independent runs on complex tasks. It supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, it is more steerable, follows developer instructions more closely, and produces cleaner code. It works in the CLI, IDE extensions, GitHub, and cloud tasks. It adapts its reasoning to the task: quick answers for small tasks and multi-hour runs for large projects. It is trained for structured code reviews, finding critical flaws by reasoning over dependencies and validating behavior against tests. It also accepts images and screenshots for UI development and has tools for search, dependency installation, and environment setup. Codex is intended for agentic coding.
$0.625market price $1.25
$0.065market price $0.13
$5.00market price $10.00
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
GPT-5.1-Codex is a version of GPT-5.1 optimized for software engineering and coding workflows, both in interactive sessions and in long, independent runs on complex tasks. It supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review.
On NagaAI, GPT 5.1 Codex costs $0.625 per 1M input tokens and $5 per 1M output tokens. You pay only for what you use, with no subscription.
GPT 5.1 Codex reads up to 400k tokens in one request, counting the prompt and the answer together.
Yes. GPT 5.1 Codex can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough throughput data
Not enough TTFT data