Last verified
ARCHIVE PRICERETIRED REASONING128KTEXT MODELNO CACHE SKU

o1-mini API Pricing

o1-mini is retired; this archive preserves the first cheap o-series price. $3/M input, $12/M output. It launched alongside o1 as a coding-friendly reasoning tier before o4-mini compressed the price further.

Archived input - per 1M tokens
$3.00/M
Source OpenAI retired
Archived output - per 1M tokens
$12.00/M
Use for invoice checks retired
Cached input
$3.00/M
Cache no separate SKU not listed
Effective - agentic blend
$3.72/M
92/8 split - no cache
§ 01 / TERMINAL

o1-mini API cost calculator.

Archive calculator pre-loaded with o1-mini rates. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

o1-mini cost on real workloads.

§ 03 / TOKENIZER

o1-mini token counter and cost.

What's a token →
Estimate · tiktoken-cl100k_base · ≈4 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 285
Words 42
Tokens (estimated) 71 tokens
Cost as input · uncached $0.00021 USD
Cost as output · uncached $0.00085 USD
§ 04 / SHELF

o1-mini vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
o1-mini Current $3.00 $12.00 $3.72 agentic 92/8 128K Reasoning archive comparisons
GPT-5.5 $5.00 cache $0.50 $30.00 $3.61 −3% 1M Current OpenAI flagship
GPT-5.4 $2.50 cache $0.25 $15.00 $1.80 −2.1× 1.05M Current OpenAI daily driver
GPT-5.4 mini $0.75 cache $0.075 $4.50 $0.541 −6.9× 400K Current cheap OpenAI workloads
Claude Sonnet 5.5 $2.00 cache $0.10 $10.00 $1.29 −2.9× 1M Anthropic's current Sonnet
Gemini 3.8 Flash $0.75 cache $0.075 $3.75 $0.481 −7.7× · promo 1M Gemini long-context work
DeepSeek V4 Pro $1.32 cache $0.044 $3.96 $0.569 −6.5× 1M Low-cost reasoning and coding
§ 05 / DEEP LINKS

o1-mini cost by scenario.

All calculators →
§ 07 / BENCHMARKS

o1-mini benchmarks

All benchmarks →

o1-mini has published scores on 2 benchmarks we track; its best placing is #92 of 105 on ARC-AGI-2. All of these scores come from independent leaderboards, not from the lab.

Benchmark Score Rank Leader Source
ARC-AGI-2 Reasoning 0.8% ARC Prize verified, best result #92 of 105 GPT-6 Astra · 95% Official leaderboard ARC Prize Foundation
ARC-AGI-1 Reasoning 14% ARC Prize verified, best result #88 of 99 6 tied · 98.5% Official leaderboard ARC Prize Foundation

o1-mini API pricing FAQ.

Short answers for teams checking o1-mini pricing, status, and migration choices.

Q · 01 Is o1-mini still available? +
o1-mini is retired. Keep this page for pricing history, old invoices, and migration planning.
Q · 02 How much did o1-mini cost? +
o1-mini is archived at $3/M input and $12/M output.
Q · 03 Is cached-input pricing included? +
No separate cached-input SKU is listed for this archive entry, so the calculator treats cached input as undiscounted.
Q · 04 What replaced it? +
OpenAI named o4-mini, which was itself shut down on October 23, 2026 with GPT-5.6 Terra as its substitute; use the shelf to compare current options.
Q · 05 Why keep this archive page? +
Archive pages preserve old price baselines, help explain invoice history, and capture migration search demand without treating old models as current recommendations.