GPT-5.3 Codex Spark

OpenAIMCP Tool CallReasoning
openai/gpt-5.3-codex-sparkClosed API

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Benchmark Pricing$1.75 / 1M in$14.00 / 1M out$0.17 cache read
Context: 128,000 tokens•Max Output: 32,000 tokens•Knowledge: 2025-08-31•Released: 2026-02-05

TECHNICAL SPECIFICATIONS

Context Window128,000128K tokens
Max Output32,00032K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionPDF
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GPT-5.3 Codex Spark natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 128,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling GPT-5.3 Codex Spark via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "openai/gpt-5.3-codex-spark",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

3 providers
OpenAIgpt-5.3-codex-spark
$1.75 / $14.00$0.17 cache
Poeopenai/gpt-5.3-codex-spark
$0.00 / $0.00
OpenCodegpt-5.3-codex-spark
$1.75 / $14.00$0.17 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.17 / 1M tokens, saving up to 90% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES