European lab behind compact open and enterprise coding models. Mistral AI’s coding models on Kilo Code include Mistral Medium 3.5, and Devstral 2 2512. Use them across VS Code, JetBrains IDEs, Cursor, Windsurf, Trae, and the Kilo CLI — with pay-as-you-go pricing and no markup over the underlying provider rates.
Sorted by coding-index where published. Click any model for the full review with benchmarks, real-world Kilo usage, and provider-specific pricing.
Mistral AI
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...
Mistral AI
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...
Mistral AI is known for compact, efficient models and a pragmatic open-model strategy. Its Devstral line is explicitly aimed at software engineering agents, while Medium and larger hosted models provide stronger general reasoning for teams that want European infrastructure and flexible deployment choices.
Pay-as-you-go, no markup over the underlying provider rates. Cheapest first.
| Model | Input / 1M | Output / 1M | Context | Coding index |
|---|---|---|---|---|
| Mistral: Devstral 2 2512 | $0.400 | $2.00 | 262K | — |
| Mistral: Mistral Medium 3.5 | $1.50 | $7.50 | 262K | 46.9 |
Three ways: hosted in Kilo, locally on your hardware, or through your own provider keys.
The fastest path: install Kilo Code, sign in, pick mistral ai from the model picker. No API keys, no markup. Works in VS Code, JetBrains, Cursor, Windsurf, Trae, and the Kilo CLI.
See live model leaderboard →Already have an account with Mistral AI, OpenRouter, AWS Bedrock, Google Vertex, Together AI, or another compatible provider? Plug your key into Kilo Code and keep your existing billing relationship.
BYOK setup guide →Download Mistral AI open weights from Hugging Face and serve them with Ollama, LM Studio, vLLM, or SGLang. Connect Kilo Code to your local OpenAI-compatible endpoint and keep all prompts on hardware you control.
Local setup guide →See coding-model lineups from Mistral AI’s closest competitors.
Mistral AI’s flagship is among the strongest coding models on the Kilo Code leaderboard, ranked by Code, Plan, Ask, Debug, and Review usage.
VS Code, Cursor, Windsurf, Trae, JetBrains IDEs (IntelliJ, PyCharm, WebStorm, GoLand, RubyMine, Android Studio), and the Kilo CLI / terminal.
Switch between Mistral AI and 500+ other models with one click. Pay only for what you use, at the underlying provider rate.
Devstral is the Mistral model most directly tuned for coding-agent work. Mistral Medium is the broader reasoning option when you need stronger general capability.
Mistral models work in every Kilo-supported IDE and CLI; open variants can also be self-hosted locally.
Mistral pricing depends on the model and provider. Kilo Code shows current per-million-token rates with no markup.
Mixed. Mistral publishes several open models, while some frontier hosted models are closed API offerings.
Devstral focuses on software-engineering agents. Medium and larger Mistral models target broader reasoning, instruction following, and enterprise workloads.
Mistral models work in every Kilo-supported IDE and CLI; open variants can also be self-hosted locally.
Install Kilo Code and get instant access to Mistral: Mistral Medium 3.5 and 1 other Mistral AI models, plus 500+ frontier and open-source options. Free to start, no credit card required.