o4 Mini
Fast and lightVisionToolsOpenAI · Released April 2025 · Knowledge cutoff June 2024
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
It is part of OpenAI's GPT family, where Sol, Luna and Terra mark the current generation's capability tiers and Pro servings trade speed for deeper computation.
Facts and pricing
- Provider
- OpenAI
- Context window
- 200K tokens
- Input price
- 12.1 credits / 1M tokens ($1.10 raw)
- Output price
- 48.4 credits / 1M tokens ($4.40 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try o4 Mini now
What o4 Mini is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Long documents: the 200K-token window holds lengthy reports, contracts or papers whole
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like o4 Mini:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
OpenAI family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| GPT-5.6 Luna Pro | 1.1M | 11.0 | 66.0 | July 2026 |
| GPT-5.6 Luna | 1.1M | 11.0 | 66.0 | July 2026 |
| GPT-5.6 Terra Pro | 1.1M | 27.5 | 165 | July 2026 |
| GPT-5.6 Terra | 1.1M | 27.5 | 165 | July 2026 |
| GPT-5.6 Sol Pro | 1.1M | 55.0 | 330 | July 2026 |
| GPT-5.6 Sol | 1.1M | 55.0 | 330 | July 2026 |
| GPT Chat Latest | 400K | 55.0 | 330 | May 2026 |
| GPT-5.5 Pro | 1.1M | 330 | 1980 | April 2026 |
| GPT-5.5 | 1.1M | 55.0 | 330 | April 2026 |
| GPT-5.4 Image 2 | 272K | 88.0 | 165 | April 2026 |
Frequently asked questions
- What is o4 Mini?
- o4 Mini is an AI model by OpenAI. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
- How much does o4 Mini cost on Zeplik?
- Input tokens cost 12.1 credits per million and output tokens 48.4 credits per million (1 credit = $0.10; the raw provider rates are $1.10 and $4.40 per million). New accounts start with free credits.
- How long can a conversation with o4 Mini be?
- o4 Mini has a 200K-token context window (200,000 tokens), which covers the conversation plus any documents you attach.
- Does o4 Mini support images and tools?
- o4 Mini accepts image input and supports tool calling.
Related models
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...