This model was retired on 2026-10-16. The pricing below is the last-known rate, kept for migration reference.

O4 Mini (2025-04-16)Deprecated

OpenAI
VisionTool useReasoningPrompt cachingStructured outputWeb search
Context
200K
Max output
100K
Serving providers
2
Cheapest input
$1.10 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: ARC Prize
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
ARC-AGI-26%high$0.856

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Azure$1.10$4.401
OpenAI$1.10$4.401

Price history

input + output $/1M since we started tracking
Input Output
$0.000$2.00$4.00$6.00Apr 16Apr 18Jun 22$4.40$1.10

Cost calculator

estimate your monthly spend on this model
$572
estimated / month

Model IDs

copy the exact identifier for your platform
azure/o4-mini-2025-04-16o4-mini-2025-04-16

Frequently asked questions

O4 Mini (2025-04-16) pricing, context and availability

Is O4 Mini (2025-04-16) still available?

O4 Mini (2025-04-16) was retired on 2026-10-16. The pricing on this page is the last-known rate, kept for migration reference.

How much did O4 Mini (2025-04-16) cost?

O4 Mini (2025-04-16)'s last-known pricing, before it was retired on 2026-10-16, was $1.10 per 1M input tokens and $4.40 per 1M output tokens.

What was the context window of O4 Mini (2025-04-16)?

O4 Mini (2025-04-16) had a 200K token context window and could return up to 100K output tokens.

What could O4 Mini (2025-04-16) do?

O4 Mini (2025-04-16) supported image input (vision), tool use, reasoning, prompt caching, structured output and web search.

Other OpenAI models

compare pricing across the OpenAI lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI