Mistral: Mistral Small 3
by Mistral · Released 2025-01-30
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
Context33K tokensMax output16.4K tokensReleased2025-01-30
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
≈ 0,02 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 | 16,20 DA | 25,92 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≈ 0,0058 DA
Reply to a customer email≈ 0,02 DA
Translate a full page of text≈ 0,02 DA
Write a one-page draft≈ 0,02 DA
Top up points
3 000 DA ≈ 138 197 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
- 33K tokens
- Max output
- 16.4K tokens
- Longest reply
- ≈ 12.0K words
- Tokenizer
- Mistral
- Knowledge cutoff
- 2023-10-31
- Released
- 2025-01-30
Questions about Mistral Small 3
How much does Mistral Small 3 cost in Algerian Dinars?
16,20 DA for the text you send and 25,92 DA for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,02 DA. You pay for what you actually use: no subscription, no minimum.
How big is Mistral Small 3's context window?
Mistral Small 3 reads up to 33K tokens in one request, and writes back up to roughly 12,000 words at once.
What can Mistral Small 3 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 Mistral Small 3 without an international bank card?
Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on Mistral Small 3 or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.
Who makes Mistral Small 3?
Mistral Small 3 is built by Mistral, released on Jan 30, 2025. Its training data runs to 2023-10-31. OpenDunes serves it unchanged — same model, same weights, billed in dinars.
Other Mistral models, priced in dinars
See all Mistral modelsMistral: Voxtral Small 24B 2507 STT
mistralai/voxtral-small-24b-2507-sttTranscription
Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.
AudioText
0,02 DA / hourby MistralAug 13, 2026JSON
Mistral: Voxtral Mini 3B 2507
mistralai/voxtral-mini-3b-2507Transcription
Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.
AudioText
0,01 DA / hourby MistralAug 13, 2026JSON
Mistral: Voxtral Mini Transcribe
mistralai/voxtral-mini-transcribeTranscription
Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings,...
AudioText
0,97 DA / hourby MistralMay 15, 2026JSON
Mistral: Mistral Medium 3.5
mistralai/mistral-medium-3-5Text
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
TextImagesFilesText
in486 DAout2 430 DAper 1M tokens
by MistralApr 30, 2026262K contextReasoningToolsJSON
Mistral: Mistral Medium 3.5 (batch)
mistralai/mistral-medium-3-5:batchText
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
TextImagesFilesText
in243 DAout1 215 DAper 1M tokens
by MistralApr 30, 2026262K contextReasoningToolsJSON
Mistral: Voxtral Mini TTS
mistralai/voxtral-mini-tts-2603Speech
Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.
TextAudio
5 184 DA / 1M charsby MistralApr 19, 20264K contextJSON
Mistral: Mistral Small 4
mistralai/mistral-small-2603Text
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
TextImagesText
in48,60 DAout194,40 DAper 1M tokens
by MistralMar 16, 2026262K contextReasoningToolsJSON
Mistral: Devstral 2 2512
mistralai/devstral-2512Text
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
TextFilesText
in129,60 DAout648 DAper 1M tokens
by MistralDec 9, 2025262K contextToolsJSON