o3-mini: Pricing, Context, and Benchmarks

o3-mini is OpenAI's o-series model released on 2025-01-31. It runs on a 200K-token context window, priced at $1.10/M input and $4.40/M output. Smaller reasoning model. Cheaper o-series option with strong STEM benchmark scores.

Input

$1.10/M

Output

$4.40/M

Cached input

$0.5500/M

Context

200K

Max output

100K

Specifications

Provider	OpenAI
Family	o-series
Released	2025-01-31
Status	active
Context window	200K tokens
Max output	100K tokens
Modalities	text
Capabilities	function calling json mode reasoning
Tokenizer	`o200k_base`
API endpoint	`https://api.openai.com/v1/responses`
Documentation	Official docs ↗
Last updated	2026-05-29

Cost calculator

For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0055 per call. For typical usage:

Workload	Tokens / call (in/out)	$/call	$/1K calls	$/1M calls
Short Q&A	200 / 100	$0.000660	$0.66	$660
Standard chat	1K / 500	$0.003300	$3.30	$3,300
RAG with retrieval	4K / 500	$0.006600	$6.60	$6,600
Long doc summary	20K / 1K	$0.026400	$26.40	$26,400
Long context (100K input)	100K / 2K	$0.116600	$116.60	$116,600

For more precise estimates including caching discounts, use the LLM API Cost Calculator.

Other OpenAI models

Common comparisons

API setup

curl https://api.openai.com/v1/responses \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "o3-mini", "messages": [{"role": "user", "content": "Hello"}]}'

See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.