This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Sarvam has launched a newer release, Sarvam 30B. We suggest considering it instead.
Sarvam M (Reasoning, Based on Mistral Small 3.1) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Sarvam M (Reasoning, Based on Mistral Small 3.1) for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 1 provider
Lowest Cost per Task
Cost per Intelligence Index task
Total 1 provider
Sarvam M is available through Sarvam.
Please see the models page for Sarvam M (Reasoning, Based on Mistral Small 3.1) for details of the model and its intelligence compared to other models.
Pricing
Cost per Intelligence Index Task: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Pricing: Cache Hit, Input, and Output: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Output Speed vs. Cost per Task: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Sarvam M (Reasoning, Based on Mistral Small 3.1)
Key Comparison Metrics & API Features
 Sarvam | -- | -- | -- | -- | 8k | Open | ||
Frequently Asked Questions
Common questions about Sarvam M (Reasoning, Based on Mistral Small 3.1) providers
Sarvam M (Reasoning, Based on Mistral Small 3.1) is available through 1 API provider: Sarvam. Each provider offers different performance characteristics and pricing.
Sarvam M (Reasoning, Based on Mistral Small 3.1) is currently available through 1 API provider that we benchmark and track.
The most affordable provider for Sarvam M (Reasoning, Based on Mistral Small 3.1) by blended price is Sarvam ($0.00 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for Sarvam M (Reasoning, Based on Mistral Small 3.1) is Sarvam ($0.00 per 1M input tokens).
The provider with the lowest output token pricing for Sarvam M (Reasoning, Based on Mistral Small 3.1) is Sarvam ($0.00 per 1M output tokens).
The only provider of Sarvam M (Reasoning, Based on Mistral Small 3.1) supports JSON mode for structured output.
When choosing a provider for Sarvam M (Reasoning, Based on Mistral Small 3.1), consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Sarvam M (Reasoning, Based on Mistral Small 3.1)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview