o4-mini on Replicate API

o3 · OpenAI

Serverless

Last refreshed 2026-05-19. Next refresh: weekly.

Why use o4-mini on Replicate API?

Replicate API offers o4-mini with pay-as-you-go pricing at $1.00/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare o4-mini across 4 providers to find the best fit for your use case
Input / 1M
$1.00
Output / 1M
$4.00
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "openai/o4-mini",
    input={"prompt": "Hello"}
Model ID
openai/o4-mini

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# openai/o4-mini format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "openai/o4-mini",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Use provider model ID "openai/o4-mini", not the LLMReference slug "o4-mini".
  • Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare o4-mini Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenAI API$1.10$4.40
OpenRouter$1.10$4.40
Replicate API$1.00$4.00
Vercel AI Gateway$1.10$4.40

Pricing

TypePrice (per 1M)
Input tokens$1.00
Output tokens$4.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode Execution

About o4-mini

Fast and cost-efficient reasoning model with vision support for math, coding, and visual understanding. Retired from ChatGPT February 13, 2026 but still available via API. Released April 16, 2025.

Get Started

Model Specs

Released2025-04-16
Context200k
ArchitectureDecoder Only
Knowledge cutoff2025-08