Sarvam: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Sarvam for your use-case.
Most Intelligent
Intelligence Index
Total 1 model
Fastest
Sarvam 105B (high)Output speed
Total 1 model
Lowest Price
Sarvam 105B (high)Blended price (per 1M tokens)
Total 1 model
Sarvam currently offers Sarvam 105B (high).
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Key definitions
Frequently Asked Questions
Common questions about Sarvam
Sarvam offers 1 model that we track: Sarvam 105B (high).
The fastest model on Sarvam by output speed is Sarvam 105B (high) at 175.8 tokens per second.
The model with the lowest time to first answer token on Sarvam is Sarvam 105B (high) at 13.00s. Lower latency means faster initial response time.
The most affordable model on Sarvam by blended price is Sarvam 105B (high) at $0.04 per 1M tokens (7:2:1 cache hit/input/output ratio).
Yes, Sarvam offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 1 models on Sarvam support JSON mode for structured output.
Yes, all 1 models on Sarvam support function calling (tool use).
Yes, Sarvam offers 1 reasoning model: Sarvam 105B (high). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 1 models on Sarvam are open weight models.
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.
When choosing a model on Sarvam, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.