Devstral 2 2512 vs Qwen3 VL 30B A3B Thinking: side-by-side summary

Devstral 2 2512 and Qwen3 VL 30B A3B Thinking are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Devstral 2 2512, from Mistral AI, has a 262,144-token context window and is priced at $0.40/M tokens input, $2/M tokens output on OpenRouter.

Qwen3 VL 30B A3B Thinking, from Qwen, has a 262,144-token context window and is priced at $0.20/M tokens input, $2.40/M tokens output on OpenRouter.

Context window

• Devstral 2 2512: 262,144 tokens
• Qwen3 VL 30B A3B Thinking: 262,144 tokens

Price

• Devstral 2 2512: $0.40/M tokens input, $2/M tokens output
• Qwen3 VL 30B A3B Thinking: $0.20/M tokens input, $2.40/M tokens output

Provided by

• Devstral 2 2512: Mistral AI
• Qwen3 VL 30B A3B Thinking: Qwen

• Devstral 2 2512 model details, providers and pricing
• Qwen3 VL 30B A3B Thinking model details, providers and pricing