Microsoft: Phi 4
by Microsoft · Released 2025-01-10
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Context16K tokensMax output14.7K tokensReleased2025-01-10
What it can do
Real jobs this model can take on, based on what it can read and how it’s priced.
Power a chat product at high volume, priced per reply
≈ 0,04 DA per typical reply
Good for
- High-volume workloads where cost per reply matters
Not for
- Generating images — it replies with text only
- Speaking its replies aloud — no audio output
- Fine-tuning on your own data — not supported
Also supports
Tool callingStructured JSONStep-by-step reasoningStreamingPrompt cachingFine-tuning
Where your request runs
You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.
| Provider | In /M | Out /M | Cache /M | Latency | TPS | Uptime |
|---|---|---|---|---|---|---|
| DeepInfra | 22,68 DA | 45,36 DA | — | — | — | 100,0 % |
Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.
What it costs
Everyday jobs, priced. Each request charges exactly what it uses — no subscription, no minimum.
Answer a quick question≈ 0,0095 DA
Reply to a customer email≈ 0,02 DA
Translate a full page of text≈ 0,04 DA
Write a one-page draft≈ 0,04 DA
Top up points
3 000 DA ≈ 82 671 typical replies · the exact charge appears after every request, down to the centime.
Call it in code
OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.
Sign in to run this request on your own wallet.
The same request, in your language
Parameters you can send
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- 16K tokens
- Max output
- 14.7K tokens
- Longest reply
- ≈ 11.0K words
- Tokenizer
- Other
- Knowledge cutoff
- 2024-06-30
- Released
- 2025-01-10
Questions about Phi 4
How much does Phi 4 cost in Algerian Dinars?
22,68 DA for the text you send and 45,36 DA for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,04 DA. You pay for what you actually use: no subscription, no minimum.
How big is Phi 4's context window?
Phi 4 reads up to 16K tokens in one request, and writes back up to roughly 11,000 words at once.
What can Phi 4 handle?
It reads text and replies with text. It also supports replying in structured JSON and streaming its answer as it writes.
Can I use Phi 4 without an international bank card?
Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on Phi 4 or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.
Who makes Phi 4?
Phi 4 is built by Microsoft, released on Jan 10, 2025. Its training data runs to 2024-06-30. OpenDunes serves it unchanged — same model, same weights, billed in dinars.
Other Microsoft models, priced in dinars
See all Microsoft modelsMicrosoft: MAI-Image-2.5 Pro
microsoft/mai-image-2.5-proImage
Microsoft's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
TextImagesImages
1 620 DA/M input·0 DA/M outputby MicrosoftJul 23, 20264K context
Microsoft: MAI-Voice-2-Flash
microsoft/mai-voice-2-flashSpeech
MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15 languages...
TextAudio
4 860 DA / 1M charsby MicrosoftJul 23, 2026
Microsoft: MAI-Voice-2
microsoft/mai-voice-2Speech
MAI-Voice-2 is an expressive text-to-speech model from Microsoft. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18 locales,...
TextAudio
7 128 DA / 1M charsby MicrosoftJun 2, 2026
Microsoft: MAI-Transcribe 1.5
microsoft/mai-transcribe-1.5Transcription
MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable transcription across 43 languages, diverse...
AudioText
116,64 DA / hourby MicrosoftJun 2, 2026
Microsoft: MAI-Image-2.5
microsoft/mai-image-2.5Image
Microsoft's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
TextImagesImages
1 620 DA/M input·0 DA/M outputby MicrosoftJun 2, 20264K context
WizardLM-2 8x22B
microsoft/wizardlm-2-8x22bText
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
TextText
in200,88 DAout200,88 DAper 1M tokens
by MicrosoftApr 16, 202466K contextJSON