Sarvam 105B: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
Sarvam 105B (High) supports text input, outputs text, and has a 128k tokens context window.
Pricing for Sarvam 105B (High) is $0.042 per 1M input tokens (competitively priced, median: $0.30) and $0.17 per 1M output tokens (competitively priced, median: $0.80).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 128k ~192 A4 pages of size 12 Arial font |
| Total parameters | 106B |
| Active parameters | 10.3B 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
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
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Sarvam 105B (High) | - | 106B 10.3B active at inference time | 128k | $0.0436 | - | 138 |
More from Sarvam
Frequently Asked Questions
Common questions about Sarvam 105B
Sarvam 105B was released on March 6, 2026.
Sarvam 105B was created by Sarvam.
Sarvam 105B has a time to first answer token of 11.24s (based on Sarvam's API), which is somewhat higher than average compared to other open weight models of similar size (median: 8.18s).
Sarvam 105B costs $0.042 per 1M input tokens (very competitive, median: $0.30) and $0.17 per 1M output tokens (very competitive, median: $0.80), based on Sarvam's API.
Sarvam 105B costs $0.042 per 1M input tokens and $0.17 per 1M output tokens (based on Sarvam's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.0436 per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, Sarvam 105B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Sarvam 105B supports text input.
Sarvam 105B supports text output.
No, Sarvam 105B does not support image input. It can only process text.
No, Sarvam 105B is not multimodal. It only supports text input.
Sarvam 105B has a context window of 128k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Sarvam 105B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Sarvam 105B has 106B parameters (10.3B active).
Sarvam 105B is a Mixture of Experts (MoE) model with 106B total parameters, but only 10.3B active parameters are used during inference.
Sarvam 105B is released under the Apache 2.0 license. This license allows commercial use. View license
Yes, Sarvam 105B is available via API through 1 provider. Compare API providers
Sarvam 105B is available through 1 API provider. Compare providers