Skip to content
OhMyGPT

Search

Search pages, models and actions, or paste a request ID…

GPT-4o-mini (2024-07-18)

July 2024 snapshot of GPT-4o-mini, the initial release of OpenAI's affordable small model.

Try in ChatCompare
Input price
$0.165
Output price
$0.66
Context
128K
Max output
16K
124 (#82 of 82)
1286
—
Released
2024-07-18
InputTextImagePDFOutputText

Providers

This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].

Included providers1
  • SuccessTTFT
  • OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

ItemStandardStandard DiscountBatchBatch DiscountPriorityPriority DiscountPricePrice Discount
Inputper 1M tokens$0.165$0.0825$0.275—
Outputper 1M tokens$0.66$0.33$1.10—
Cache readper 1M tokens$0.0825$0.041252$0.1375—
Web searchper request———$0.0275
Estimated cost of common use (500 output tokens each)
One chat message3K input tokens$0.000828—$0.00138—
Agent first turn100K tokens of context, none cached$0.0168—$0.0281—
Each later agent turncontext read from cache, plus 2K new tokens$0.00892—$0.0149—
20-turn agent taskfirst turn plus 19 more$0.186—$0.31—

Try it

Runs on your balance and is billed like any API request.

Provider preferences don’t apply to this model. Need a custom setup? Contact [email protected].

Accepts images and PDFs, or paste them in

Try one

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

GPT-4o-mini (2024-07-18)This model
124
Input
$0.165
Output
$0.66
—
Input
$0.165
Output
$0.55
—
Input
$0.165
Output
$0.66
—
Input
$0.165
Output
$0.66
—
Input
$0.165
Output
$0.66

Capability scores come from independent benchmarks: Epoch AI's ECI index aggregates dozens of public evaluations on a scale anchored at GPT-5 = 150 for direct comparison (CC BY 4.0, as of 2026-11-21). epoch.ai/eci

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text