Sarvam 30B: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
Sarvam 30B (High) supports text input, outputs text, and has a 66k tokens context window.
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 66k ~98 A4 pages of size 12 Arial font |
| Total parameters | 32.2B |
| Active parameters | 2.4B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Sarvam 30B (High) | - | 32.2B 2.4B active at inference time | 66k | - | - | - | - |
More from Sarvam
Frequently Asked Questions
Common questions about Sarvam 30B
Sarvam 30B was released on March 6, 2026.
Sarvam 30B was created by Sarvam.
Yes, Sarvam 30B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Sarvam 30B supports text input.
Sarvam 30B supports text output.
No, Sarvam 30B does not support image input. It can only process text.
No, Sarvam 30B is not multimodal. It only supports text input.
Sarvam 30B 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 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Sarvam 30B has 32.2B parameters (2.4B active).
Sarvam 30B is a Mixture of Experts (MoE) model with 32.2B total parameters, but only 2.4B active parameters are used during inference.
Sarvam 30B is released under the Apache 2.0 license. This license allows commercial use. View license
Sarvam 30B is an open weights model that can be self-hosted. View providers
Sarvam 30B is an open weights model that can be downloaded and self-hosted. Compare providers