Skip to content

Devstral Small 2

View Status

Devstral Small 2 is a 24B agentic coding model with 68.0% on SWE-bench Verified, a context window of 256K tokens, and multimodal input support. Devstral Small 2 matches models up to five times its size on coding benchmarks.

Tool Use
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/devstral-small-2',
  prompt: 'Why is the sky blue?'
})

What To Consider When Choosing a Provider

  • Configuration: At 24B parameters, Devstral Small 2 reaches comparable SWE-bench performance to models 5x its size.
  • 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 Devstral Small 2

Best For

  • Compact agentic coding: Tasks requiring a context window of 256K tokens at 24B parameters
  • Multimodal debugging workflows: Combining code and screenshots or diagrams
  • Apache 2.0 for commercial products: Teams that need an Apache 2.0 license for a coding model

Consider Alternatives When

  • Higher SWE-bench scores: You need a stronger score (consider Devstral 2)
  • No image input needed: Devstral Small meets your accuracy bar
  • Reasoning-first problem solving: Tasks where deep reasoning matters more than agentic code execution (consider Magistral models)

Conclusion

Devstral Small 2 competes with systems five times its scale on real-world software engineering benchmarks. It adds a context window of 256K tokens and multimodal input over the first generation. Choose it when you need a compact agentic coding model under Apache 2.0.

Frequently Asked Questions

  • What is Devstral Small 2's SWE-bench Verified score?

    68.0%, matching models up to 5x its parameter size.

  • Does Devstral Small 2 support image inputs?

    Yes. Multimodal input is one of the key additions over the original Devstral Small, enabling workflows that combine code and visual assets.

  • What is the context window for Devstral Small 2?

    256K tokens, the same as Devstral 2, which is a significant upgrade from the original Devstral Small.

  • What is the license for Devstral Small 2?

    Apache 2.0, permitting unrestricted commercial use.

  • How does Devstral Small 2 compare to Devstral 2?

    Devstral 2 (123B) achieves higher SWE-bench scores. Devstral Small 2 (24B) achieves 68.0% at a much smaller parameter count.

  • What is the API pricing for Devstral Small 2?

    This page lists the current rates. Multiple providers can serve Devstral Small 2, so AI Gateway surfaces live pricing rather than a single fixed figure.