Compare Devstral 2 2512 from Mistral AI and Sonar Pro Search from Perplexity on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.




Devstral 2 2512 and Sonar Pro Search 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.
Sonar Pro Search, from Perplexity, has a 200,000-token context window and is priced at $3/M tokens input, $15/M tokens output on OpenRouter.
| Attribute | Devstral 2 2512 | Sonar Pro Search |
|---|---|---|
| Input price | $0.40/M tokens | $3/M tokens |
| Output price | $2/M tokens | $15/M tokens |
| Context window | 262,144 tokens | 200,000 tokens |
| Intelligence Index | 8.6 | Not available |
| Coding Index | 31.3 | Not available |
| Agentic Index | 2.3 | Not available |
| Latency (p50) | 0.63 s | 13.18 s |
| Throughput (p50) | 80.0 tok/s | 45.0 tok/s |
Benchmark data updated
Devstral 2 2512 is cheaper than Sonar Pro Search on OpenRouter: Devstral 2 2512 costs $0.40/M tokens input and $2/M tokens output, while Sonar Pro Search costs $3/M tokens input and $15/M tokens output.
Devstral 2 2512 has the longer context window at 262,144 tokens, compared with 200,000 tokens for Sonar Pro Search.
Devstral 2 2512 is faster on OpenRouter, generating a median 80.0 tokens per second compared with 45.0 tokens per second for Sonar Pro Search.