Context
8K
Max output
32K
Serving providers
1
Cheapest input
$0.00 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%reasoning: true
EvalComputeProxy152.2reasoning: true
GPQA Diamond42%reasoning: true
Humanity's Last Exam3%reasoning: true
IFBench32%reasoning: true
LiveCodeBench30%reasoning: true
Long-Context Reasoning0%reasoning: true
MMLU-Pro70%reasoning: true
Omniscience-62.3reasoning: true
SciCode18%reasoning: true
TerminalBench Hard2%reasoning: true
τ²-bench0%reasoning: true

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
SarvamCheapest$0.00$0.001
ComponentUnitStandardBatchCached
Text cached in/1M tok$0
Text cache write/1M tok$0
Text input/1M tok$0
Text output/1M tok$0

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.010$0.020$0.030Jul 30Jan 21Jun 22$0.000$0.000

Cost calculator

estimate your monthly spend on this model
$0
estimated / month

Model IDs

copy the exact identifier for your platform
sarvam/sarvam-m

Frequently asked questions

Sarvam M pricing, context and availability

How much does Sarvam M cost?

Sarvam M costs $0.00 per 1M input tokens and $0.00 per 1M output tokens at its cheapest provider via Sarvam.

What is the context window of Sarvam M?

Sarvam M accepts up to 8K tokens of context and can return up to 32K output tokens.

What can Sarvam M do?

Sarvam M supports reasoning.

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI