← Model list
sarvam-m
sarvamai·sarvamai/sarvam-m·GA·Open weights
Efficient Indian-language reasoning model for chat, coding, and multilingual work
At a glance
Reference price$0 / $0 per 1M
Cache read — · Nvidia
Lowest paidNo paid channels
1 more $0 channels
Context128,000
Output limit8,192
Capabilities
Reasoning✓ Tool use? Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2025-07-25 / 2025-07-25
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence2.6
Value—
Coding—
Agentic—
Output speed—
TTFT—
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 1 providers0 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | First-party | Free | — | — | 128,000 | 8,192 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
This model is $0 across all listed channels (Nvidia).
Price historyone sample accumulated per data sync
Input listOutput listMin blended