Sarvam 105B (high) API Pricing
Sarvam · released 2026-03-06
Pricing
< 0.01¢ / 1K
0.017¢ / 1K
< 0.01¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0072¢ |
| RAG query | 4,000 in / 500 out | 0.0253¢ |
| Long document summary | 50,000 in / 1,000 out | 0.227¢ |
| Code review of a 2k-line file | 30,000 in / 2,000 out | 0.16¢ |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $2.16 |
Cost = (input tokens ÷ 1,000,000 × $0.042) + (output tokens ÷ 1,000,000 × $0.17).
Benchmarks
#295 of 533
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Llama 3.1 Instruct 8B | 6.9 | $0.028 |
| Gemma 4 E4B (Reasoning) | 8.9 | $0.04 |
| Sarvam 30B (high) | 6.6 | $0.047 |
| Granite 4.2 3B | 9.1 | $0.052 |
| Nova Micro | 5.9 | $0.061 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 8.9 | $0.088 |
| MiniCPM5-1B (Reasoning) | 8.8 | — |
| Qwen3 4B 2507 (Reasoning) | 8.8 | — |
| Sarvam 105B (high) | 8.8 | $0.074 |
| Claude 3 Opus | 8.7 | $30.00 |
| Devstral Small (May '25) | 8.7 | — |
| Gemini 2.0 Pro Experimental (Feb '25) | 8.7 | — |
More from Sarvam
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Sarvam 30B (high) | 6.6 | $0.047 |
| Sarvam M (Reasoning) | 5.3 | — |
Count tokens & estimate cost for Sarvam 105B (high) See Sarvam 105B (high) on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Sarvam 105B (high)?
Sarvam 105B (high) is developed by Sarvam, released 2026-03-06.
How much does Sarvam 105B (high) cost per million tokens?
Sarvam 105B (high) costs $0.042 per 1M input tokens and $0.17 per 1M output tokens ($0.074 blended), per Artificial Analysis's official pricing data.
How does Sarvam 105B (high) rank on benchmarks?
Sarvam 105B (high) scores 8.8 on the Artificial Analysis Intelligence Index, ranking #295 of 533 models we track.
Is there a cheaper model with similar intelligence to Sarvam 105B (high)?
Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.074/1M for Sarvam 105B (high).
Where does this data come from?
Pricing and benchmark data for Sarvam 105B (high) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.