CtrlAltDebrief
Scheduled for retirement on Aug 24, 2027. Still available at the prices below until then.

GPT-5.3-Codex

OpenAIReleased Feb 15, 2026KnowledgeJan 2026
VisionTool useReasoningPrompt cachingStructured output
Compare GPT-5.3-CodexCount tokens for GPT-5.3-Codex
Context
400K
Max output
128K
Serving providers
5
Cheapest input
$1.75 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
111 t/s
tokens / second
Time to first token
75.10s
latency
Headline indices
Intelligence Index
32.5
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt17%default—
GPQA Diamond92%default—
Humanity's Last Exam42%default—
IFBench75%default—
Long-Context Reasoning83%default—
MMMU-Pro78%default—
Omniscience10.9default—
Omniscience Accuracy0.5default—
Omniscience Non Hallucination0.1default—
SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 202653%——
TerminalBench Hard53%default—
τ²-bench86%default—

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $1.75 to $1.93 per 1M tokens across 5 providers, so the dearest route costs 10% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
AihubmixCheapest$1.75$14.001
Standardaihubmix/gpt-5.3-codex
ComponentUnitStandard
Text cached in/1M tok$0.175
Text input/1M tok$1.75
Text output/1M tok$14.00
Databricks$1.75$14.001
OpenRouter$1.75$14.001
VercelVercel reseller quote$1.75$14.001
Azure$1.93$15.401
Vercel (fast)Vercel reseller quote$3.50$28.001
Vercel (priority)Vercel reseller quote$3.50$28.001

Price history

listed seller prices, input and output per 1M tokens
Input Output
$0.00$5.00$10.00$15.00Aug 19Aug 26Sep 16Sep 17$14.00$1.75

Cost calculator

estimate your monthly spend on this model
$1,470
estimated / month

Model IDs

copy the exact identifier for your platform
databricks/databricks-gpt-5-3-codexopenai/gpt-5.3-codexaihubmix/gpt-5.3-codexopenai/gpt-5.3-codexazure/eu/gpt-5.3-codexopenai/gpt-5.3-codex-fastopenai/gpt-5.3-codex

Frequently asked questions

GPT-5.3-Codex pricing, context and availability

Is GPT-5.3-Codex still available?

Yes. GPT-5.3-Codex is scheduled for retirement on 2027-08-24.

How much does GPT-5.3-Codex cost?

GPT-5.3-Codex costs $1.75 per 1M input tokens from Aihubmix, and $14.00 per 1M output tokens from Aihubmix. Across 5 serving providers, input prices range from $1.75 to $1.93 per 1M tokens.

What is the context window of GPT-5.3-Codex?

GPT-5.3-Codex accepts up to 400K tokens of context and can return up to 128K output tokens.

Which providers serve GPT-5.3-Codex?

GPT-5.3-Codex is available from 5 serving providers, each with its own pricing and model ID. Aihubmix is currently the cheapest.

What can GPT-5.3-Codex do?

GPT-5.3-Codex supports image input (vision), tool use, reasoning, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup
gpt-oss-120b$0.03/1M · 23 providersgpt-oss-20b$0.0145/1M · 15 providersGPT-5 Mini$0.25/1M · 9 providersGPT-5$1.25/1M · 9 providersGPT-5 Nano$0.05/1M · 8 providersGPT-5.6 Luna$0.20/1M · 7 providersGPT-5.6 Terra$2.00/1M · 7 providersGPT-4o-mini$0.15/1M · 6 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI