LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

o3-mini

openai·openai/o3-mini·Deprecated·Closed·o-mini series
Smaller o-series reasoner for economical coding, math, and planning tasks

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$1.10 / $4.40
Blended $1.93 · Cache read $0.55
Lowest paid·PoeGateway
$0.99 / $4.00
Blended $1.74 · 1.1× spread
Context
200,000
Output limit
100,000
Knowledge cutoff
2024-05
Released / updated
2024-12-20 / 2025-01-29
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

o3-mini by openai is offered by 17 providers on this page. Public prices are shown for 16 of them. Its official list price is $1.10 per 1M input tokens and $4.40 per 1M output tokens.

Median output speed is 247 tokens per second, with 18.92s to the first token.

The context window is 200,000 tokens, with an output limit of 100,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-05.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier High

Intelligence—
Value—
Output speed247 tok/s
TTFT18.92 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 17 providers16 with public prices

  • ProviderInput / Output
  • PoeGateway
    openai/o3-mini-high
    $0.99 / $4.00
    Context 200,000Output limit 100,000deprecated
  • PoeGateway
    $0.99 / $4.00
    Context 200,000Output limit 100,000deprecated
  • Jiekou.AIGateway
    $1.05 / $4.18
    Cache read $0.52Context 200,000Output limit 100,000
  • OpenAIOfficialFirst-party
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000deprecated
  • Azure Cognitive ServicesCloud
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000deprecated
  • DigitalOceanCloud
    openai-o3-mini
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000
  • NEAR AI CloudGateway
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000
  • Merge GatewayGateway
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000
  • Eden AIGateway
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000
  • AzureCloud
    $1.10 / $4.40
    Cache read $0.55Context 200,000Output limit 100,000deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Poe
openai/o3-mini-high
Gateway$0.99$4.00——200,000100,000deprecated
PoeGateway$0.99$4.00——200,000100,000deprecated
Jiekou.AIGateway$1.05$4.18$0.52—200,000100,000
OpenAIOfficialFirst-party$1.10$4.40$0.55—200,000100,000deprecated
Azure Cognitive ServicesCloud$1.10$4.40$0.55—200,000100,000deprecated
DigitalOcean
openai-o3-mini
Cloud$1.10$4.40$0.55—200,000100,000
NEAR AI CloudGateway$1.10$4.40$0.55—200,000100,000
Merge GatewayGateway$1.10$4.40$0.55—200,000100,000
Eden AIGateway$1.10$4.40$0.55—200,000100,000
AzureCloud$1.10$4.40$0.55—200,000100,000deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = high

2 / 17 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Jiekou.AI$355.30
2OpenAI · Official$374.00
3Azure Cognitive Services$374.00
4DigitalOcean$374.00
5NEAR AI Cloud$374.00
6Merge Gateway$374.00
Switch to Jiekou.AI to save $18.70/mo (5%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.40$02026-08-052026-09-03
2026-09-03Input list $1.10Output list $4.40Min blended $1.74

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—60.4percent correctSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

OpenAI: o1-minisame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20o3same lab$2.00 / $8.00o3-prosame lab$20.00 / $80.00
Data partly from models.dev (MIT) · OpenAI official docs ↗