Context
131K
Max output
16K
Serving providers
6
Cheapest input
$2.50 /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
99 t/s
tokens / second
Time to first token
5.19s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
GPQA Diamond54%default
Humanity's Last Exam3%default
IFBench34%default
LiveCodeBench31%default
Long-Context Reasoning0%default
MMLU-Pro75%default
Omniscience-10.8default
SciCode33%default
TerminalBench Hard8%default
τ²-bench25%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
AzureCheapest$2.50$10.001
ComponentUnitStandardBatchCached
Text cached in/1M tok$1.25
Text input/1M tok$2.50
Text output/1M tok$10.00
GmiCheapest$2.50$10.001
OpenAICheapest$2.50$10.001
OpenRouterCheapest$2.50$10.001
Vercel AI GatewayCheapest$2.50$10.001
ReplicateCheapest$2.50$10.001

Price history

input + output $/1M since we started tracking
Input Output
Input down 50% since first tracked
$0.000$5.00$10.00$15.00May 13Oct 5Jul 30Jun 22$10.00$2.50

Cost calculator

estimate your monthly spend on this model
$1,300
estimated / month

Model IDs

copy the exact identifier for your platform
azure/gpt-4ogmi/openai/gpt-4ogpt-4oopenrouter/openai/gpt-4overcel_ai_gateway/openai/gpt-4oreplicate/openai/gpt-4o

Frequently asked questions

GPT-4o pricing, context and availability

How much does GPT-4o cost?

GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens at its cheapest provider via Azure.

What is the context window of GPT-4o?

GPT-4o accepts up to 131K tokens of context and can return up to 16K output tokens.

Which providers serve GPT-4o?

GPT-4o is available from 6 serving providers, each with its own pricing and model ID. Azure is currently the cheapest.

What can GPT-4o do?

GPT-4o supports image input (vision), tool use, audio input, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup

Popular comparisons

head-to-head pages featuring GPT-4o
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