Devstral Small 2
Devstral Small 2 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 256k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Devstral
- Released
- 2025-12-09
- Context
- 256k
- Parameters
- 24B
- Specialization
- code
- Openness
- Open source
- License
- Apache 2.0(OSI)Commercial use allowed
- Training
- Pretrained
Cheapest of 2 routes · Mistral AI Studio
About
Devstral Small 2 is Mistral AI's 24B open-weights coding agent model, released December 9, 2025 under Apache 2.0. It scores 68.0% on SWE-bench Verified and supports agentic software engineering tasks, multi-step reasoning, and tool use. Runs on a single RTX 4090 GPU or a Mac with 32GB RAM. Multimodal, with support for image inputs.
Devstral Small 2 is an open-source model in the Devstral family. The structured metadata tracks a 256k-token context window, multimodal input, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Vercel AI Gateway and Mistral AI Studio, with the cheapest tracked route listed at $0.1 input and $0.3 output per 1M tokens. No headline benchmark score is tracked for Devstral Small 2 yet.
Top use-case fit: coding, agents, and build tasks
Coding
Included by capability and metadata signals in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 2Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Mistral AI Studio | $0.100 | $0.300 | Serverless |
| Vercel AI Gateway | $0.100 | $0.300 | Serverless |
Available via routers & gateways(10)
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Martian
RouterAI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.
Neutrino AI
RouterCommercial LLM router that dynamically routes each query to the best-suited model with load balancing and fallback handling, charging 3% of underlying AI spend.
Not Diamond
RouterPredictive model router that determines the best LLM for each query; claims up to 25% accuracy gains and 10x cost reduction; powers OpenRouter's auto mode and is positioned specifically for coding agents.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Cheapest of 2 routes · Mistral AI Studio