LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-4o mini

openai·openai/gpt-4o-mini·GA·Closed·gpt-mini series
Small omni GPT for cheap multimodal assistance and production-scale traffic

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.15 / $0.60
Blended $0.26 · Cache read $0.075
Lowest paid·Cloudflare AI GatewayCloud
$0.075 / $0.30
Blended $0.13 · 3.3× spread
Context
128,000
Output limit
16,384
Knowledge cutoff
2023-09
Released / updated
2024-07-18 / 2024-07-18
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-4o mini by openai is offered by 32 providers on this page. Its official list price is $0.15 per 1M input tokens and $0.60 per 1M output tokens. The lowest paid channel is Cloudflare AI Gateway at $0.075 / $0.30 per 1M, about 2.0× below the list price.

Median output speed is 77 tokens per second, with 1.69s to the first token.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 124,096 to 128,000, so the usable window depends on the provider you pick. It supports 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 2023-09.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed77 tok/s
TTFT1.69 s

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

Available at 32 providers32 with public prices

  • ProviderInput / Output
  • Cloudflare AI GatewayCloud
    $0.075 / $0.30
    Cache read $0.038Context 128,000Output limit 16,384
  • PoeGateway
    $0.14 / $0.55
    Cache read $0.068Context 124,096 ⚠Output limit 4,096
  • OpenAIOfficialFirst-party
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • CrossModelGateway
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • LLM GatewayGateway
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • Azure Cognitive ServicesCloud
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384deprecated
  • DigitalOceanCloud
    openai-gpt-4o-mini
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • LowRouterGateway
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
  • NanoGPTGateway
    $0.15 / $0.60
    Cache read $0.075Context 128,000Output limit 16,384
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Cloudflare AI GatewayCloud$0.075$0.30$0.038—128,00016,384
PoeGateway$0.14$0.55$0.068—124,096 ⚠4,096
OpenAIOfficialFirst-party$0.15$0.60$0.075—128,00016,384
CrossModelGateway$0.15$0.60$0.075$0.15128,00016,384
LLM GatewayGateway$0.15$0.60$0.075—128,00016,384
LLM GatewayGateway$0.15$0.60$0.075—128,00016,384
Azure Cognitive ServicesCloud$0.15$0.60$0.075—128,00016,384deprecated
DigitalOcean
openai-gpt-4o-mini
Cloud$0.15$0.60$0.075—128,00016,384
LowRouterGateway$0.15$0.60$0.075—128,00016,384
NanoGPTGateway$0.15$0.60$0.075—128,00016,384

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.

Experimental modes2 items

ModeProviderInputOutputCache readCache write
fastOpenAI$0.25$1.00$0.13—
fastVercel AI Gateway$0.25$1.00$0.13—

Your usage cost

Common scenarios
1Cloudflare AI Gateway$25.50
2Poe$46.37
3OpenAI · Official$51.00
4CrossModel$51.00
5LLM Gateway$51.00
6LLM Gateway$51.00
Switch to Cloudflare AI Gateway to save $25.50/mo (50%)

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.60$02026-08-052026-08-18
2026-08-18Input list $0.15Output list $0.60Min blended $0.13

Benchmark2 items

NameConditionsScoreMetricSource
Aider Polyglot—3.6percent correctSource ↗
SciCode—22.9percent correctSource ↗

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

Related models

GPT Mini Latestsame series—GPT-5.4 minisame series$0.75 / $4.50GPT-Audio Minisame series—Nova Litecheaper alternative$0.06 / $0.24Nova Microcheaper alternative$0.035 / $0.14Command R7Bcheaper alternative$0.038 / $0.15Lyria 3 Clip Previewcheaper alternative$0 / $0GPT-4o (2024-11-20)same lab$2.50 / $10.00GPT-4o Mini Transcribesame lab—
Data partly from models.dev (MIT) · OpenAI official docs ↗