Aihubmix Phi 4 Mini (reasoning): API pricing, providers and specs
Aihubmix Phi 4 Mini (reasoning) is a text model by Microsoft. 2 providers serve it, from $0.12 to $0.30 /1M; the lowest price is at AIHubMix.
How Aihubmix Phi 4 Mini (reasoning) compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.12 /1M, its lowest price undercuts 91% of comparable models (median $1.10).
- Its 128K-token context window is larger than 12% of them (median 262K), about 190 pages of text.
- 2 providers serve it; 36% of comparable models have fewer.
- Its weights are open under the MIT license: commercial use allowed.
Aihubmix Phi 4 Mini (reasoning) prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
Specs
- Type
- Text
- Maker
- Microsoft
- Inputs
- Text
- Outputs
- Text
- Context
- 128K≈ 190 pages of text
- Max output
- 4K
- Capabilities
- —
- Released
- Apr 29, 2025
- License
- MITcommercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 3.8B
Alternatives to Aihubmix Phi 4 Mini (reasoning)
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Aihubmix Phi 4 Mini (reasoning)this model | $0.12/1M | 128K | — | 2 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
 Ling 3.1 Flash | $0.225/1M | 262K | — | 5 |
 Qwen2-1.5B-Instruct | $0.20/1M | — | — | 2 |
| Qwen3.5 Flash | $0.287/1M | 1M | — | 1 |
| GPT OSS 120B | $0.14/1M | 131K | 1366 | 32 |
More from Microsoft
Florence-2 LargeMicrosoft$0.001/GPU-secKosmos 2MicrosoftFree/1MMAI-Code-1.1-FlashMicrosoft$1.20/1MMAI-Image-2.6Microsoft$5/1MMAI-Image-2.6-FlashMicrosoft$1.75/1MMai Image 2.5Microsoft$0.05/runMAI-Image-2.5-FlashMicrosoft$0.03/imgMai Image 2.5 ProMicrosoft$0.18/runAihubmix Phi 4 Mini (reasoning) FAQ
The lowest price for Aihubmix Phi 4 Mini (reasoning) is $0.12 /1M, at AIHubMix.
AIHubMix, at $0.12 /1M. 2 providers serve Aihubmix Phi 4 Mini (reasoning); the table above lists every one with its price.
Aihubmix Phi 4 Mini (reasoning) reads up to 128K tokens per request and writes up to 4K.
Yes. Aihubmix Phi 4 Mini (reasoning)'s weights can be downloaded from its maker's Hugging Face page, under the MIT license.
About 3.8B, as the safetensors metadata of its official Hugging Face repo states.
2 API providers serve Aihubmix Phi 4 Mini (reasoning). Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us