← Model list
Sarvam 30B
sarvam·sarvam/sarvam-30b·GA·Open weights·sarvam series
Efficient Indian-language reasoning model for chat, coding, and multilingual work
At a glance
Official pricePrice undisclosed
Lowest paid$0.02 / $0.10
FastRouter Gateway · 1.4× spread
Context65,536
⚠ Providers report 65,536–128,000; the table below is authoritative
Output limit65,536
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2026-02-18 / 2026-02-18
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high
Intelligence6.4
Value160
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 6.4 ÷ min blended $0.040 = 160
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 3 providers2 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| FastRouter | Gateway | $0.02 | $0.10 | — | — | 128,000 ⚠ | 128,000 | |
| NanoGPT | Gateway | $0.028 | $0.111 | $0.017 | — | 65,536 | 4,096 | |
| Sarvam AIOfficial | First-party | — | — | — | — | 65,536 | 65,536 | hostTable.undisclosed |
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
1FastRouter$9.00
2NanoGPT$9.83
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = loweffort = mediumeffort = higheffort = null
1 / 3 providers expose no reasoning control (reasoning_options: []).
Related models
Price historyone sample accumulated per data sync
Input listOutput listMin blended