Mistral Medium Latest
Mistral Medium Latest is Mistral AI's frontier-class multimodal model for agentic and coding work, merging instruction following, configurable reasoning, and coding into one dense 128B model with a context window of 256K tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'mistral/mistral-medium-3.5', prompt: 'Why is the sky blue?'})Playground
Try out Mistral Medium Latest by Mistral AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Mistral Medium Latest
Ask Mistral Medium Latest anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Mistral AI | 256K | 0.3s | 54tps | $1.50/M | $7.50/M | — | — | +1 | 04/29/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Mistral AI
| Model |
|---|
| 256K | 0.8s | 43tps | $0.10/M | $0.30/M | — | — | | 12/09/2025 | |||||
| 256K | 0.7s | 59tps | $0.50/M | $1.50/M | — | — | | 12/02/2025 | |||||
| 128K | 0.3s | 176tps | $0.10/M | $0.10/M | — | — | | 10/16/2024 | |||||
| 128K | 0.3s | 88tps | $0.15/M | $0.15/M | — | — | | 10/16/2024 | |||||
| 32K | 0.3s | $0.10/M | $0.30/M | — | — | | 09/17/2024 | ||||||
| $0.10/M | — | — | | 12/11/2023 |
About Mistral Medium Latest
Announced April 29, 2026, Mistral Medium Latest is Mistral AI's first flagship merged model. Earlier lineups split the work across three families: Medium for instruction following, Magistral for reasoning, and Devstral for agentic coding. Mistral Medium Latest folds all three into a single dense 128B model and succeeds Mistral Medium 3.1 as Mistral AI's flagship mid-size tier.
Mistral Medium Latest scores 77.6% on SWE-Bench Verified and 91.4 on the τ³-Telecom agentic benchmark, per Mistral AI's announcement. The SWE-Bench result puts Mistral Medium Latest ahead of Mistral AI's earlier Devstral coding models.
Reasoning effort is configurable per request. Ask for a fast reply on simple prompts, or allocate more test-time compute for long agentic runs. The vision encoder handles variable image sizes and aspect ratios, so Mistral Medium Latest reads screenshots, documents, and diagrams alongside text. Native function calling and structured output support long-horizon tool use.
The weights are open under a modified MIT license. Through AI Gateway, you access Mistral Medium Latest without separate Mistral AI API credentials, with unified billing plus cost and latency visibility across every request.
What To Consider When Choosing a Provider
- Configuration: Mistral Medium Latest merges what used to be three separate Mistral AI model lines. Instruction following, reasoning, and agentic coding now share one set of weights, and reasoning effort is configurable per request. Turn reasoning up for hard agentic runs and down for quick replies.
- Configuration: Reasoning spends extra output tokens on test-time compute, so budget for higher output usage when you enable it. AI Gateway's built-in observability shows the cost and latency impact per request. For simple high-volume tasks that never need reasoning or vision, a smaller model like Ministral or Mistral AI Small may be a better fit.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Mistral Medium Latest
Best For
- Agentic Tool-Calling Workflows: Long-horizon runs that mix planning, reliable tool calls, and structured output
- Software Engineering Agents: Multi-file coding tasks backed by 77.6% on SWE-Bench Verified
- Multimodal Document Understanding: Tasks that combine screenshots, diagrams, or documents with text
- Model Consolidation: Replacing separate chat, reasoning, and coding models with one endpoint
- Configurable Reasoning Effort: Dialing test-time compute up or down per request
Consider Alternatives When
- Largest General-Purpose Capability: You want Mistral AI's biggest model (consider Mistral AI Large 3)
- Paramount Cost Efficiency: Simple high-volume tasks don't need reasoning or vision (consider Ministral or Mistral AI Small)
- Fill-in-the-Middle Completion: You need a dedicated IDE completion model (consider Codestral)
Conclusion
Mistral Medium Latest folds Mistral AI's chat, reasoning, and coding lines into one model. You get configurable reasoning, image understanding, and strong agentic coding scores behind a single endpoint. Access Mistral Medium Latest through AI Gateway with unified billing and built-in observability.