Mistral has launched remote coding agents and a new AI model called Mistral Medium 3.5, marking a significant step toward autonomous software development. Mistral explains that the system allows coding tasks to run in the cloud without requiring a developer to stay at their computer.
The new model is a dense 128-billion-parameter system with a 256,000-token context window. It handles instruction-following, reasoning, and coding within a single set of weights. According to Mistral, the model scores 77.6% on SWE-Bench Verified, a standard benchmark for software engineering tasks, outperforming competing models including Qwen3.5 397B. It can run on as few as four graphics processing units, making self-hosting viable for many organizations.
The remote agents integrate with tools developers already use, including GitHub, Jira, Linear, Sentry, Slack, and Microsoft Teams. Once a task is complete, the agent can automatically open a pull request for human review. Multiple sessions can run in parallel, which Mistral says removes developers as a bottleneck in repetitive tasks such as refactoring, test generation, and dependency upgrades.
A new “Work mode” in Mistral’s Le Chat assistant extends these capabilities beyond coding. It allows the assistant to handle multi-step tasks such as inbox management, research, and calendar preparation, using several tools simultaneously.
Mistral Medium 3.5 is available via API at $1.50 per million input tokens and $7.50 per million output tokens. Open weights are available on Hugging Face under a modified MIT license.
Stay up to date
AI for content creation: the latest tools, tips and trends. Every two weeks in your inbox:
