GPT-5.3 Codex API

GPT-5.3 Codex is a large language model by OpenAI, available on the Venice API as openai-gpt-53-codex. Requests are anonymized, so the provider never sees your identity.GPT-5.3 Codex is OpenAI specialized coding model built on GPT-5.3, optimized for advanced software development, code generation, and technical problem-solving.

GPT-5.3 Codex API pricing

Model ID	Variant	Privacy	Price
`openai-gpt-53-codex`	Standard	Anonymized	$2.19 input /$ 17.50 output per 1M tokens

GPT-5.3 Codex specifications

Spec	Value
Provider	OpenAI
Released	Feb 24, 2026
Privacy	Anonymized
Context window	400K tokens
Max output	125K tokens
Reasoning effort	none, low, medium, high, xhigh

How to use the GPT-5.3 Codex API

Send requests to POST https://api.venice.ai/api/v1/responses with "model": "openai-gpt-53-codex" and your API key.

curl https://api.venice.ai/api/v1/responses \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai-gpt-53-codex",
    "input": "Explain TEE attestation in two sentences.",
    "reasoning": { "effort": "high" }
  }'

GPT-5.3 Codex API FAQ

How much does the GPT-5.3 Codex API cost?

2.19 per 1M input tokens and

17.50 per 1M output tokens, with cached input at $0.22 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the GPT-5.3 Codex model ID?

Use openai-gpt-53-codex as the model parameter.

Is the GPT-5.3 Codex API private?

GPT-5.3 Codex is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

What is the context window of GPT-5.3 Codex?

400K tokens of context, with up to 125K output tokens per response.

What does GPT-5.3 Codex support?

GPT-5.3 Codex supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, low, medium, high and xhigh (default high).

Which endpoint does the GPT-5.3 Codex API use?

Call POST /responses. /chat/completions is also supported. Pro and Codex models are Responses-native upstream. Use /responses for typed reasoning, tool-call and message items; /chat/completions stays fully supported.

Related models

Gemini 3.1 Pro Preview API: $2.50 input /$ 15.00 output per 1M tokens
Claude Sonnet 5 API: $3.00 input /$ 15.00 output per 1M tokens
Claude Sonnet 4.6 API: $3.60 input /$ 18.00 output per 1M tokens
Kimi K3 API: $3.75 input /$ 18.75 output per 1M tokens

Explore

By modality