LLM Reference

o4-mini

Released
2025-04-16
Last refreshed
2026-06-29
Status
Researched 74d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

o4-mini is a legacy integration reference; evaluate GPT-5 Mini before starting new work.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • New production launches
Specifications
Family
o3
Released
2025-04-16
Context
200k
Architecture
Decoder Only
Knowledge cutoff
2025-08
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$4.00
Input / 1M
$1.00

Cheapest of 4 routes · Replicate API

This model is deprecated. OpenAI recommends switching to GPT-5 Mini.

About

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.

o4-mini is a proprietary model in the o3 family. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenAI API, OpenRouter, Replicate API, and 1 more, with the cheapest tracked route listed at $1 input and $4 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 68.1, LiveCodeBench 87.3, and Aider Polyglot 72.0.

Top use-case fit: coding, agents, and build tasks

Coding

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 4

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
Replicate API$1.00$4.00--
Serverless
OpenAI API$1.10$4.40$0.550 / $2.20-
Serverless
OpenRouter$1.10$4.40--
Serverless
Vercel AI Gateway$1.10$4.40-read $0.275
Serverless

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(10)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
SWE-bench Verified68.1Observed 2025-04-16Source
LiveCodeBench87.32026-04 (high reasoning mode)Observed 2026-04-14Source
Aider Polyglot72.02026-04 (high)Observed 2026-04-14Source
Massive Multi-discipline Multimodal Understanding81.6Observed 2026-04-15Source
MathVista84.3Observed 2026-06-03Source
BFCL53.2Observed 2026-04-14Source
MMLU PRO83.2Observed 2026-04-14Source
MultiChallenge44.9MultiChallengeObserved 2026-04-26Source
Google-Proof Q&A81.4Observed 2025-04-16Source
AIME 202598.4Observed 2025-04-16Source

Migration checks

No linked migration route is available for this model yet.

Compare o4-mini with other models

Frequently asked questions

What is the context window of o4-mini?

o4-mini has a context window of 200k tokens.

How much does o4-mini cost?

o4-mini pricing ranges from $1/1M to $1.1/1M input tokens depending on the provider.

When was o4-mini released?

o4-mini was released on 2025-04-16.

Which providers offer o4-mini?

o4-mini is available from 4 providers: OpenAI API, OpenRouter, Replicate API, Vercel AI Gateway.

What benchmarks has o4-mini been tested on?

o4-mini has been evaluated on 10 benchmarks, including SWE-bench Verified, LiveCodeBench, Aider Polyglot, Massive Multi-discipline Multimodal Understanding, MathVista.