Sarvam

Sarvam 105B (high)

AI model by Sarvam. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.04
Output$0.17
Blended (3:1)$0.07

Source: Artificial Analysis

Performance

Output Speed
Time to First Token

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Sarvam 105B (high) is a budget-tier option from Sarvam at $0.17/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Cost model. For a workload of 1M input tokens + 100K output tokens, Sarvam 105B (high) costs $0.06 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Sarvam 105B (high)Current
$0.04$0.17
NVIDIA Nemotron Nano 9B V2 (Reasoning)
$0.04$0.16186 tok/s
gpt-oss-20b (high)
$0.06$0.19136 tok/s
Qwen3.5 4B (Non-reasoning)
$0.03$0.1528 tok/s
Qwen3.5 4B (Reasoning)
$0.03$0.1523 tok/s
Ministral 3 8B
$0.15$0.15120 tok/s

Example Costs

Single Request
$0.0001
1.0K in / 500 out
1K Requests/day
$0.1250
1.0M in / 500.0K out
10K Requests/day
$1.25
10.0M in / 5.0M out