GPT-5.3 Codex Spark

Models

Model details

Model
gpt-5.3-codex-spark
Provider
openai-codex
API
openai-codex-responses
Base URL
https://chatgpt.com/backend-api
Input
text
Reasoning
Yes
Context window
128,000
Max tokens
128,000
Show configuration
{
  "providers": {
    "openai-codex": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "gpt-5.3-codex-spark",
          "name": "GPT-5.3 Codex Spark",
          "reasoning": true,
          "input": [
            "text"
          ],
          "thinkingLevelMap": {
            "xhigh": "xhigh",
            "minimal": "low"
          },
          "contextWindow": 128000,
          "maxTokens": 128000,
          "cost": {
            "input": 1.75,
            "output": 14,
            "cacheRead": 0.175,
            "cacheWrite": 0
          }
        }
      ],
      "api": "openai-codex-responses",
      "baseUrl": "https://chatgpt.com/backend-api"
    }
  }
}

Pricing

USD per million tokens. A tier is selected from the total input tokens in each request and applies to that entire request.

Request inputInputOutputCache readCache write
All requests$1.75$14$0.175$0

Session cost calculator

Estimate the requests made during an agent session. A user turn can make several model calls while using tools, so costs are calculated per model request.

Session shape
Rounded median shapes from recent Pi agent sessions.
Warm-request cache reuse
Effective token reuse combines partial hits and occasional complete misses.
Estimated session$0.00
Uncached input
—
Cache reads
—
Uncached prefixes
—
Cache writes
—
Output
—
Without caching
—

The first request starts cold unless marked otherwise. Output is billed separately from context growth because reasoning tokens are not always retained. This remains a directional estimate: providers differ in eligibility, rounding, and retention.

Compatibility flags

This API has no model compatibility flags.

More

Also available from other providers