GPT-5.3 Codex
GPT-5.3 CodexAlternatives?
CheaperGemini 3.8 Flashhigh+4%-69%*$1.24Sampling parameters are ignored+1
OpenKimi K3max+2%+25%$2.00Sampling parameters are fixed+3
CheaperGrok 4.6high+4%-38%$1.48
CheaperMuse Spark 1.3xhigh+3%-58%$1.37Only auto tool_choice is supported+5CheaperGemini 3.1 Pro Previewthinking+3%-6%$1.30Cannot use both thinking controlsGemini 3.8 Flashhigh+4%-69%*$1.24Sampling parameters are ignored+1Grok 4.6high+4%-38%$1.48Muse Spark 1.3xhigh+3%-58%$1.37Only auto tool_choice is supported+5Gemini 3.1 Pro Previewthinking+3%-6%$1.30Cannot use both thinking controls
Qwen3.8 2.4T A95BthinkingOpen+2%-38%$2.16Context: 400K → 262K+6Gemini 3.8 Flashmedium+2%-69%*$0.93Sampling parameters are ignored+1Grok 4.6medium+2%-38%$1.14Gemini 3.1 Pro Previewthinking+3%-6%$1.30Cannot use both thinking controlsMuse Spark 1.3xhigh+3%-58%$1.37Only auto tool_choice is supported+5GPT-6 Astramedium+3%+316%$1.54Monitoring can return HTTP 403+2Kimi K3maxOpen+2%+25%$2.00Sampling parameters are fixed+3Qwen3.8 2.4T A95BthinkingOpen+2%-38%$2.16Context: 400K → 262K+6
MiniMax M3thinkingOpen+2%-89%$0.51No strict JSON+1
DeepSeek V4 Pro 0813maxOpen+1%-59%$0.67No image input+5Qwen3.8 FlashthinkingOpensame-95%$0.37Context: 400K → 262K+6GPT-6 Astraxhigh+5%—$2.31Monitoring can return HTTP 403+2GPT-5.5xhigh+2%—$2.63Prompts with >272K input tokensGPT-5.6 Solxhigh+2%—$1.18GPT-5.4xhighsame—$2.50 / $15GPT-5.6 Terraxhighsame—$0.63Prompts with >272K input tokensGPT-5.2xhigh-1%—$1.75 / $14GPT-5.6 Lunaxhigh-2%—$0.085GPT-5.4 Minixhigh-4%—$0.45All OpenAI models →History
4 versionsBenchmarks
in Chat & KnowledgeWatch out 1
Deprecated›
The official model page marks this model deprecated; plan a migration. Source ↗
FAQ
How much does GPT-5.3 Codex cost?›
$1.75 per 1M input tokens and $14 per 1M output tokens; cached input $0.17 per 1M.
Is GPT-5.3 Codex free to use?›
There is no free API; the cheapest paid price is $1.75 per 1M input tokens.
How good is GPT-5.3 Codex, and what is it best at?›
#34 of 334 in Chat & Knowledge, #9 of 239 in Coding, #60 of 242 in Agents & Tool Use, #25 of 245 in Writing & Language, #31 of 124 in Vision & Documents. Strongest at: Tool calling, Reasoning, Science, Long context, Knowledge, Instructions, Vision.
Is GPT-5.3 Codex better than GLM 5.3?›
On GPQA Diamond, GPT-5.3 Codex scores 91.5 vs 91.7 — about the same.
How can I use GPT-5.3 Codex?›
Through the API of Azure, OpenAI.
What is the context window of GPT-5.3 Codex?›
400K tokens, with up to 128K output tokens.
When was GPT-5.3 Codex released? Is there a newer version?›
Released 2026-02-05. It has been superseded by GPT-6 Sol.
Is GPT-5.3 Codex open source?›
No, GPT-5.3 Codex is a closed model available through an API. The closest open-weights option here is Kimi K3.
Can GPT-5.3 Codex read images?›
It accepts text and images, PDF files as input.
What is GPT-5.3 Codex?›
GPT-5.3 Codex is a closed language model from OpenAI, released Feb 2026.
What are the best alternatives to GPT-5.3 Codex?›
Gemini 3.8 Flash (cheaper), Kimi K3 (open weights).