Side-by-side comparison
Devstral Small 1.1 vs Qwen3 30B A3B Thinking 2507
Mistral
Devstral Small 1.1
🔧 Tools
{} JSON
Input / 1M
$0.1000
Output / 1M
$0.3000
Qwen
Qwen3 30B A3B Thinking 2507
🔧 Tools
{} JSON
Input / 1M
$0.0800
Output / 1M
$0.4000
| Devstral Small 1.1 | Qwen3 30B A3B Thinking 2507 | |
|---|---|---|
| Provider | Mistral | Qwen |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 131,072 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.1000 | 0.0800 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.3000 | 0.4000 |
Frequently asked questions
Which is cheaper, Devstral Small 1.1 or Qwen3 30B A3B Thinking 2507?
Devstral Small 1.1 is cheaper than Qwen3 30B A3B Thinking 2507 on a 50/50 input/output blend by about $0.04 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
What is the difference between Devstral Small 1.1 and Qwen3 30B A3B Thinking 2507?
Devstral Small 1.1 comes from Mistral; Qwen3 30B A3B Thinking 2507 comes from Qwen. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.