Capabilities
7-day heat trend
−13.4%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 37% of tracked models
- Faster than 96% of tracked models
- Efficiency rank: #67 of 120
Best suited for
Code generation, refactoring and review, and developer-tooling workloads with large context.
About Devstral 2 2512
Devstral 2 2512 is a Code model from Mistral (EU). HotON.ai tracks it at $0.40 per 1M input tokens and $2.00 per 1M output tokens, with a 262K-token context window, ~170 tokens/sec throughput and 100.0% availability. Its composite efficiency score is 89/100 at an estimated $0.002 per successful task.
Compare Devstral 2 2512
Related market news
Frequently asked questions
How much does Devstral 2 2512 cost per 1M tokens?+
Devstral 2 2512 is tracked at $0.40 per 1M input tokens and $2.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $1.60 per 1M tokens. Figures are illustrative demo data.
What is Devstral 2 2512 best for?+
Code generation, refactoring and review, and developer-tooling workloads with large context.
How fast is Devstral 2 2512?+
Devstral 2 2512 delivers about 170 tokens/sec with 100.0% tracked availability, suitable for latency-sensitive, real-time applications.
Is Devstral 2 2512 cheaper than other AI models?+
Within the HotON.ai tracked set, Devstral 2 2512 is cheaper than 37% of models on input price and ranks #67 of 120 by overall efficiency.
Related models
Pricing and availability are real (via OpenRouter, updated daily — availability is the best-serving provider's 24h uptime). Efficiency is a HotON composite of real price and context. Speed is a modeled estimate.