Sarvam 105B (High) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Sarvam 105B (High) 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 105B (high) is available through Sarvam.
Pricing
Cost per Intelligence Index Task: Sarvam 105B (High)
Pricing: Cache Hit, Input, and Output: Sarvam 105B (High)
Output Speed vs. Cost per Task: Sarvam 105B (High)
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Sarvam 105B (High)
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Sarvam 105B (High)
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Sarvam 105B (High)
Key Comparison Metrics & API Features
-- | -- | 10.78 | 2.0% | 128k | Open | |||
Frequently Asked Questions
Common questions about Sarvam 105B (High) providers
Sarvam 105B (High) is available through 1 API provider: Sarvam. Each provider offers different performance characteristics and pricing.
Sarvam 105B (High) is currently available through 1 API provider that we benchmark and track.
The provider with the lowest time to first answer token for Sarvam 105B (High) is Sarvam (11.24s). Lower latency means faster initial response time.
The most affordable provider for Sarvam 105B (High) by blended price is Sarvam ($0.0436 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 105B (High) is Sarvam ($0.042 per 1M input tokens).
The provider with the lowest output token pricing for Sarvam 105B (High) is Sarvam ($0.17 per 1M output tokens).
The only provider of Sarvam 105B (High) supports JSON mode for structured output.
The only provider of Sarvam 105B (High) supports function calling (tool use).
When choosing a provider for Sarvam 105B (High), 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 105B (High)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview