o4-mini
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
- Family
- o3
- Released
- 2025-04-16
- Context
- 200k
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-08
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Training
- Fine-tuned
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 4Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| 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)
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Martian
RouterAI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.
Neutrino AI
RouterCommercial LLM router that dynamically routes each query to the best-suited model with load balancing and fallback handling, charging 3% of underlying AI spend.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(10)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 68.1 | — | https://openai.com/index/o4-mini-system-card/ |
| LiveCodeBench | 87.3 | 2026-04 (high reasoning mode) | https://livecodebench.github.io/performances_generation.json |
| Aider Polyglot | 72.0 | 2026-04 (high) | https://aider.chat/docs/leaderboards |
| Massive Multi-discipline Multimodal Understanding | 81.6 | — | https://mmmu-benchmark.github.io/ |
| MathVista | 84.3 | — | https://llm-stats.com/benchmarks/mathvista |
| BFCL | 53.2 | — | https://gorilla.cs.berkeley.edu/leaderboard.html |
| MMLU PRO | 83.2 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| MultiChallenge | 44.9 | MultiChallenge | https://labs.scale.com/leaderboard/multichallenge |
| Google-Proof Q&A | 81.4 | — | https://openai.com/index/o4-mini-system-card/ |
| AIME 2025 | 98.4 | — | https://openai.com/index/o4-mini-system-card/ |
Migration checks
No linked migration route is available for this model yet.
Comparison and alternatives
Browse all comparisons →Cheapest of 4 routes · Replicate API