LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

o4-mini

openai·openai/o4-mini·Deprecated·Closed·o-mini series
Fast o-series model for compact reasoning, coding, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$1.10 / $4.40
Blended $1.93 · Cache read $0.28
Lowest paid·PoeGateway
$0.99 / $4.00
Blended $1.74 · 1.2× spread
Context
200,000
Output limit
100,000
Knowledge cutoff
2024-05
Released / updated
2025-04-16 / 2025-04-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImagePDF

o4-mini by openai is offered by 17 providers on this page. Public prices are shown for 15 of them. Its official list price is $1.10 per 1M input tokens and $4.40 per 1M output tokens. Prices vary about 1.2× across the providers that host it.

Median output speed is 123 tokens per second, with 20.99s 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. Its training knowledge cuts off at 2024-05.

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

Intelligence—
Value—
Output speed123 tok/s
TTFT20.99 s

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

Available at 17 providers15 with public prices

  • ProviderInput / Output
  • PoeGateway
    $0.99 / $4.00
    Cache read $0.25Context 200,000Output limit 100,000deprecated
  • OpenAIOfficialFirst-party
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000deprecated
  • Azure Cognitive ServicesCloud
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000deprecated
  • Jiekou.AIGateway
    $1.10 / $4.40
    Context 200,000Output limit 100,000deprecated
  • NEAR AI CloudGateway
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000
  • Merge GatewayGateway
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000
  • AIHubMixGateway
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000
  • AzureCloud
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000deprecated
  • Kilo GatewayGateway
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000
  • Vercel AI GatewayCloud
    $1.10 / $4.40
    Cache read $0.28Context 200,000Output limit 100,000deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$0.99$4.00$0.25—200,000100,000deprecated
OpenAIOfficialFirst-party$1.10$4.40$0.28—200,000100,000deprecated
Azure Cognitive ServicesCloud$1.10$4.40$0.28—200,000100,000deprecated
Jiekou.AIGateway$1.10$4.40——200,000100,000deprecated
NEAR AI CloudGateway$1.10$4.40$0.28—200,000100,000
Merge GatewayGateway$1.10$4.40$0.28—200,000100,000
AIHubMixGateway$1.10$4.40$0.28—200,000100,000
AzureCloud$1.10$4.40$0.28—200,000100,000deprecated
Kilo GatewayGateway$1.10$4.40$0.28$0200,000100,000
Vercel AI GatewayCloud$1.10$4.40$0.28—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 = higheffort = xhigheffort = noneeffort = max

1 / 17 providers expose no reasoning control (reasoning_options: []).

Experimental modes4 items

ModeProviderInputOutputCache readCache write
fastOpenAI$2.00$8.00$0.50—
flexOpenAI$0.55$2.20$0.14—
fastVercel AI Gateway$2.00$8.00$0.50—
flexVercel AI Gateway$0.55$2.20$0.14—

Your usage cost

Common scenarios
1Poe$309.20
2OpenAI · Official$341.00
3Azure Cognitive Services$341.00
4NEAR AI Cloud$341.00
5Merge Gateway$341.00
6AIHubMix$341.00
Switch to Poe to save $31.80/mo (9%). 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—72percent 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 / $1.20o3-prosame lab$20.00 / $80.00text-embedding-3-largesame lab$0.13 / $0
Data partly from models.dev (MIT) · OpenAI official docs ↗