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
- Weights
- Not released
- Code
- Unknown
- 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)
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.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
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.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(10)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| SWE-bench Verified | 68.1 | —Observed 2025-04-16 | — | Source |
| LiveCodeBench | 87.3 | 2026-04 (high reasoning mode)Observed 2026-04-14 | — | Source |
| Aider Polyglot | 72.0 | 2026-04 (high)Observed 2026-04-14 | — | Source |
| Massive Multi-discipline Multimodal Understanding | 81.6 | —Observed 2026-04-15 | — | Source |
| MathVista | 84.3 | —Observed 2026-06-03 | — | Source |
| BFCL | 53.2 | —Observed 2026-04-14 | — | Source |
| MMLU PRO | 83.2 | —Observed 2026-04-14 | — | Source |
| MultiChallenge | 44.9 | MultiChallengeObserved 2026-04-26 | — | Source |
| Google-Proof Q&A | 81.4 | —Observed 2025-04-16 | — | Source |
| AIME 2025 | 98.4 | —Observed 2025-04-16 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Compare o4-mini with other models
Comparison and alternatives
Browse all comparisons →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.
Cheapest of 4 routes · Replicate API