GPT-5.3-Codex

OpenAIReleasedFeb 15, 2026KnowledgeAug 2025
Context
272K
Max output
128K
Serving providers
2
Cheapest input
$1.75 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
127 t/s
tokens / second
Time to first token
65.51s
latency
Headline indices
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 Reasoning78%default
MMMU-Pro78%default
Omniscience10.9default
Omniscience Accuracy0.5default
Omniscience Non Hallucination0.1default
SciCode53%default
TerminalBench Hard53%default
τ²-bench86%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DatabricksCheapest$1.75$14.001
EndpointStd inStd outCached inBatch in / outModel ID
StandardCheapest$1.75$14.00$0.17databricks/databricks-gpt-5-3-codex
OpenRouterCheapest$1.75$14.001

Price history

input + output $/1M since we started tracking
Input Output
$0.000$5.00$10.00$15.00Jul 19Aug 19Aug 26$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-codex

Frequently asked questions

GPT-5.3-Codex pricing, context and availability

How much does GPT-5.3-Codex cost?

GPT-5.3-Codex costs $1.75 per 1M input tokens and $14.00 per 1M output tokens at its cheapest provider via Databricks.

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

GPT-5.3-Codex accepts up to 272K 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 2 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.

What can GPT-5.3-Codex do?

GPT-5.3-Codex supports prompt caching.

Other OpenAI models

compare pricing across the OpenAI lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI