ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

o3-mini

by OpenAI

Deprecated reasoning mid tier
Deprecated — shuts down Oct 23, 2026. Still purchasable until then, but the provider has announced end-of-life. Don't start new work on it. Full deprecation status & replacements →
Availability: Migration target: gpt-5.6-sol.

Today's price · per 1M tokens

Input

$1.10

per 1M tokens

Output

$4.40

per 1M tokens

Blended

$1.93

blended $/1M — 3:1 weighted input:output

Cached input

$0.550

50% of input — prompt caching

Source: official OpenAI pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-09

Overview

Reasoning model with extended thinking. Still available for cost-conscious reasoning workloads.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching ✓ Reasoning ✓ Coding Fast inference Long context ✓ Open weights Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score65.9%
Perf per $/Mtok34.2
GPQA Diamond
79.7%
SWE-Bench Verified vendor
60%
LiveCodeBench
74.1%
Humanity's Last Exam
14%
ARC-AGI 2 vendor
35%
AIME 2025
86.5%
MMMLU
81.1%
BFCL
65.12%
HumanEval
61%
MATH 500 vendor
88%
Independent composite scores
  • AA Intelligence Index: 15.7 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 1.7 (Tool use, planning, autonomy)
  • AA-Omniscience Index: -42.6 (−100–100)
  • LMSYS Chatbot Arena: 1430.8 ELO (Human preference)
How it stacks up
  • Ranks #35 of 67 benchmarked models by average score
  • Ranks #94 of 151 comparably-measured models by percentile score, across 11 independent measurements
  • Ranks #113 of 151 comparably-tested models by normalized performance per dollar
  • Strongest at AIME 2025 — 86.5%, #16 of 36

214 tokens/sec output 14s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 9, 2026 · See full rankings →

Specifications

Provider
OpenAI
Context window
200K tokens
Modality
text
Parameters
Proprietary
Open source
No — proprietary
Released
Jan 31, 2025
Status
Deprecated ends Oct 23, 2026
Last updated
Jun 25, 2026
Tags
reasoning

Availability verified: Jul 25, 2026 — per OpenAI's own deprecation notice