Mistral

About Mistral

Mistral Studio is Mistral's AI production platform and developer console. Build, test, and run AI agents and apps on the Mistral API, with a unified catalog for models, agents, prompts, skills, datasets, and workflows, plus observability and the AI Registry.

One platform to build, deploy, and govern agentic AI systems—all with enterprise privacy, security, and full ownership of your data.

Connect your data sources. Orchestrate your business logic. Ship AI that holds up under real conditions.

Orchestrate agentic processes that persist state, retry on failure, and resume automatically.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T03:22:36.065720303Z

Service status

unknown

Current inference service status unverified

Official status page ↗

29 indexed models

29 matching models

Shieldstral 1.0

mistral/shieldstral-1-0

A compact multimodal moderation model for prompt moderation, response moderation, prompt-response pair classification, refusal detection, and safety filtering across text and image inputs. It uses natural-language policy questions and returns a yes or no classification.

Context window
32,000
Input modalities
text, image
Output modalities
text
Capabilities
moderation, multimodal, visionInput

Timestral 1.0 123M

mistral/timestral-1-0-123m

Timestral 1.0 123M is a time series foundation model for zero-shot forecasting. Part of the Timestral family, it offers a balance of forecast accuracy and efficiency, with support for contexts up to 32K timesteps, past-only and known-future covariates, and probabilistic quantile

Input modalities
timeseries
Output modalities
timeseries

Timestral 1.0 209M

mistral/timestral-1-0-209m

Timestral 1.0 209M is a time series foundation model for zero-shot forecasting. It ranks first among pretrained and zero-shot models on GIFT-Eval, TIME, and fev-bench, with support for contexts up to 32K timesteps, past-only and known-future covariates, and probabilistic quantile

Input modalities
timeseries
Output modalities
timeseries

Timestral 1.0 28M

mistral/timestral-1-0-28m

Timestral 1.0 28M is a time series foundation model for zero-shot forecasting. Part of the Timestral family, it is optimised for low-latency forecasting, with support for contexts up to 32K timesteps, past-only and known-future covariates, and probabilistic quantile outputs.

Input modalities
timeseries
Output modalities
timeseries

Timestral 1.0 5M

mistral/timestral-1-0-5m

Timestral 1.0 5M is a time series foundation model for zero-shot forecasting. The smallest model in the Timestral family, it delivers fast, lightweight forecasts, with support for contexts up to 32K timesteps, past-only and known-future covariates, and probabilistic quantile outp

Input modalities
timeseries
Output modalities
timeseries

Voxtral Mini Transcribe 2

mistral/voxtral-mini-2602

An efficient audio input model, pre-trained and optimized for transcription purposes only.

Input modalities
audio
Output modalities
transcription
Capabilities
audioInput, streaming, transcription

Inference prices

  • Per input audio minute : $0.0030 / audio_minute · mistral ↗

Voxtral Mini Transcribe Realtime

mistral/voxtral-mini-transcribe-realtime-2602

An efficient audio input model, pre-trained and optimized for live transcription purposes only.

Input modalities
audio
Output modalities
transcription
Capabilities
audioInput, streaming, transcription

Inference prices

  • Per input audio minute : $0.01 / audio_minute · mistral ↗

Voxtral Mini Transcribe Realtime 3

mistral/voxtral-mini-transcribe-realtime-3-0

Voxtral Realtime Transcribe 3 is a realtime transcription model built for agentic use-cases. It achieves state-of-the-art streaming transcription with configurable latency (80 ms to 2,400 ms), built-in end-of-turn detection, context biasing, and speaker diarization, all in a sing

Input modalities
audio
Output modalities
transcription
Capabilities
audioInput, streaming, transcription

Inference prices

  • Per input audio minute : $0.01 / audio_minute · mistral ↗

Voxtral Small

mistral/voxtral-small-2507

Our first model with audio input capabilities for instruct use cases.

Context window
32,000
Input modalities
audio, text
Output modalities
text
Capabilities
audioInput, batch, multimodal, streaming, structuredOutputs, toolCalling

Inference prices

  • Per input audio minute : $0.0040 / audio_minute · mistral ↗
  • input / 1M tokens : $0.10 / input_tokens_per_million · mistral ↗
  • output / 1M tokens : $0.40 / output_tokens_per_million · mistral ↗

Z.ai GLM 5.3

mistral/zai-glm-5-3

A third-party open weight text model from Z.ai, hosted by Mistral for long-context coding and agentic workflows. The model is served without Mistral modifications.

Context window
1,000,000
Maximum output
128,000
Input modalities
text
Output modalities
text
Capabilities
batch, promptCaching, reasoning, streaming, structuredOutputs, toolCalling

Inference prices

  • Cached input / 1M tokens : $0.14 / cache_read_tokens_per_million · mistral ↗
  • input / 1M tokens : $1.40 / input_tokens_per_million · mistral ↗
  • output / 1M tokens : $4.40 / output_tokens_per_million · mistral ↗

Z.ai GLM 5.3 Flash

mistral/zai-glm-5-3-flash

Z.AI's GLM 5.3 Flash is a multimodal 320B-parameter (18B active) Mixture-of-Experts model. Built for developer agent workflows, visual coding, and complex tool-use tasks. The model is served without Mistral modifications.

Context window
1,000,000
Maximum output
128,000
Input modalities
text, image
Output modalities
text
Capabilities
batch, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, visionInput

Inference prices

  • Cached input / 1M tokens : $0.03 / cache_read_tokens_per_million · mistral ↗
  • input / 1M tokens : $0.15 / input_tokens_per_million · mistral ↗
  • output / 1M tokens : $0.50 / output_tokens_per_million · mistral ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace