LLM Reference

GPT-5.3-Codex-Spark

Released
2026-02-12
Last refreshed
2026-06-04
Status
Researched 14d ago
DeprecatedProprietaryCommercial use: conditionalCodingRAGAgentsLong contextClassificationJSON / Tool use

GPT-5.3-Codex-Spark is a legacy integration reference; evaluate GPT-5.3-Codex before starting new work.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 131k context window

Do not use it for

  • New production launches
  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
Specifications
Family
GPT-5.4
Released
2026-02-12
Context
131k
Architecture
Decoder Only
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Pretrained
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing

No tracked provider token pricing is available yet.

This model is deprecated. OpenAI recommends switching to GPT-5.3-Codex.

About

ChatGPT Pro research preview using Cerebras hardware for real-time coding at 1000+ tokens/second. Not available as a standard public OpenAI API model.

GPT-5.3-Codex-Spark is a proprietary model in the GPT-5.4 family. The structured metadata tracks a 131k-token context window, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenAI API. No headline benchmark score is tracked for GPT-5.3-Codex-Spark yet.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Capabilities

Function CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.