GPT 5.3 Codex (Fast)

openai/gpt-5.3-codex-fast

A chat model with a 400K-token context window, at $3.675 per million input tokens and $29.40 per million output tokens.

Details

Maker: openai
Kind: Chat
Context window: 400,000 tokens
Max output: 128,000 tokens
Input: $3.675 per million tokens
Cached input: $0.3675 per million tokens, 90% off
Cache write: Same as input
Output: $29.40 per million tokens
Capabilities: Reasoning, tool use, vision, file input, web search, fast
Takes: Text, image, pdf
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2026-02-05
Newer model: openai/gpt-6.1-solReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

GPT-5.3-Codex advances both the frontier coding performance of GPT‑5.2-Codex and the reasoning and professional knowledge capabilities of GPT‑5.2, together in one model, which is also 25% faster. This enables it to take on long-running tasks that involve research, tool use, and complex execution.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.3-codex-fast",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model