Model Library
SarvamReleased March 6, 2026Sarvam 30B (high)
Sarvam · Released March 6, 2026
Intelligence score
7
At a glance
- Intelligence
- 7
- Speed
- 161.5tokens/sec
- Latency
- 1.89stime to first token
- Input price
- $0.03per 1M tokens
- Output price
- $0.11per 1M tokens
- Context window
- 66Ktokens
- Parameters
- 32.2billions
Summary
Comparison summary
Sarvam 30B (high) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9). Sarvam 30B (high) generates output at 161.5 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 101.0 t/s). Sarvam 30B (high) costs $0.03 per 1M input tokens (very competitive, median: $0.18) and $0.11 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Sarvam 30B (high) |
|---|---|
| Provider | Sarvam |
| Release date | March 6, 2026 |
| Intelligence score | 7 |
| Speed | 161.5 tokens/sec |
| Latency (TTFT) | 1.89s |
| Input price | $0.03 / 1M tokens |
| Output price | $0.11 / 1M tokens |
| Context window | 66,000 tokens |
| Parameters | 32.2B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: sarvam-30b |
Pricing
Token prices
Price per 1M tokens
Sarvam 30B (high), as listed in the catalog record
- Input$0.03
- Output$0.11
| Token type | Price per 1M |
|---|---|
| Input | $0.03 |
| Output | $0.11 |
Model Intelligence legacy profile: sarvam-30b
FAQ · 20
Frequently asked questions
Sarvam 30B (high) was released on March 6, 2026.
Sarvam 30B (high) was created by Sarvam.
Sarvam 30B (high) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9).
Sarvam 30B (high) generates output at 161.5 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 101.0 t/s).
Sarvam 30B (high) has a time to first token (TTFT) of 1.89s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).
Sarvam 30B (high) costs $0.03 per 1M input tokens (very competitive, median: $0.18) and $0.11 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
Sarvam 30B (high) costs $0.03 per 1M input tokens and $0.11 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.03 per 1M tokens. Pricing may vary by provider.
Yes, Sarvam 30B (high) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Sarvam 30B (high) supports text input.
Sarvam 30B (high) supports text output.
No, Sarvam 30B (high) does not support image input. It can only process text.
No, Sarvam 30B (high) is not multimodal. It only supports text input.
Sarvam 30B (high) has a context window of 66k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Sarvam 30B (high) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Sarvam 30B (high) has 32.2 billion parameters (2.4 billion active).
Sarvam 30B (high) is a Mixture of Experts (MoE) model with 32.2 billion total parameters, but only 2.4 billion active parameters are used during inference.
Sarvam 30B (high) is released under the Apache 2.0 license. This license allows commercial use.
Sarvam 30B (high) achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Sarvam 30B (high) is available via API through 1 provider.
Sarvam 30B (high) is available through 1 API provider.