GPT-5.2-Codex is an enhanced version of GPT-5.1-Codex, optimized for software engineering and coding tasks in interactive sessions and longer independent runs. It builds projects, develops features, debugs, refactors at large scale, and reviews code. Compared to its predecessor, it follows developer instructions more closely and writes cleaner code. It works with the CLI, IDEs, GitHub, and cloud platforms, and adjusts its reasoning effort to the task: quick responses for simple work and sustained effort on larger projects. It supports structured code reviews, detects critical flaws, validates behavior against tests, and accepts images for UI work. It is tailored for agentic coding.
$0.875market price $1.75
$0.0875market price $0.175
$7.00market price $14.00
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-5.2-Codex is an enhanced version of GPT-5.1-Codex, optimized for software engineering and coding tasks in interactive sessions and longer independent runs. It builds projects, develops features, debugs, refactors at large scale, and reviews code.
On NagaAI, GPT 5.2 Codex costs $0.875 per 1M input tokens and $7 per 1M output tokens. You pay only for what you use, with no subscription.
GPT 5.2 Codex reads up to 400k tokens in one request, counting the prompt and the answer together.
Yes. GPT 5.2 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.
GPT-6.1 TerraOpenAIGPT-6.1 SolOpenAIGPT-6 LunaOpenAIGPT-6 SolOpenAIGPT-6 AstraOpenAIGPT 5.6 LunaOpenAINot enough throughput data
Not enough TTFT data