Context
200K
Max output
100K
Serving providers
4
Cheapest input
$1.00 /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
148 t/s
tokens / second
Time to first token
11.56s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt1%default
GPQA Diamond78%default
Humanity's Last Exam18%default
IFBench69%default
LiveCodeBench86%default
Long-Context Reasoning55%default
MMLU-Pro83%default
MMMU-Pro69%default
Omniscience-35.8default
SciCode47%default
TerminalBench Hard15%default
τ²-bench56%default

Pricing by serving provider

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

Input pricing runs from $1.00 to $1.10 per 1M tokens across 4 providers, so the dearest route costs 10% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
ReplicateCheapest$1.00$4.001
ComponentUnitStandardBatchCached
Text input/1M tok$1.00
Text output/1M tok$4.00
Azure$1.10$4.401
OpenAI$1.10$4.401
Vercel AI Gateway$1.10$4.401

Price history

input + output $/1M since we started tracking
Input Output
Input down 9% since first tracked
$0.000$2.00$4.00$6.00Apr 16Jul 30Aug 5Jun 22$4.00$1.00

Cost calculator

estimate your monthly spend on this model
$520
estimated / month

Model IDs

copy the exact identifier for your platform
replicate/openai/o4-miniazure/o4-minio4-minivercel_ai_gateway/openai/o4-mini

Frequently asked questions

o4 Mini pricing, context and availability

How much does o4 Mini cost?

o4 Mini costs $1.00 per 1M input tokens and $4.00 per 1M output tokens at its cheapest provider via Replicate. Across 4 serving providers, input prices range from $1.00 to $1.10 per 1M tokens.

What is the context window of o4 Mini?

o4 Mini accepts up to 200K tokens of context and can return up to 100K output tokens.

Which providers serve o4 Mini?

o4 Mini is available from 4 serving providers, each with its own pricing and model ID. Replicate is currently the cheapest.

What can o4 Mini do?

o4 Mini supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.

Other OpenAI models

compare pricing across the OpenAI lineup

Popular comparisons

head-to-head pages featuring o4 Mini
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