Sarvam 105B (Reasoning) Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
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
| Reasoning | Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 66k ~98 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 |
Sarvam 105B (Reasoning) is above average in intelligence and well priced when comparing to other open weight models of similar size. It's also slower than average and very verbose. The model supports text input, outputs text, and has a 66k tokens context window.
Sarvam 105B (Reasoning) scores 18 on the Artificial Analysis Intelligence Index, placing it above average among comparable models (averaging 15). When evaluating the Intelligence Index, it generated 70M tokens, which is very verbose in comparison to the average of 7.4M.
Pricing for Sarvam 105B (Reasoning) is $0.00 per 1M input tokens (competitively priced, average: $0.15) and $0.00 per 1M output tokens (competitively priced, average: $0.57). In total, it cost $0.00 to evaluate Sarvam 105B (Reasoning) on the Intelligence Index.
At 78 tokens per second, Sarvam 105B (Reasoning) is slower than average (79).
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Openness
Artificial Analysis Openness Index: Results
Intelligence Index Comparisons
Intelligence vs. Price
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
Cost to Run Artificial Analysis Intelligence Index
Context Window
Context Window
Pricing
Pricing: Input and Output Prices
Intelligence vs. Price (Log Scale)
Pricing Comparison of Sarvam 105B (Reasoning) API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed vs. Price
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Comparisons to Sarvam 105B
Sarvam 105B
gpt-oss-20B (high)- gpt-oss-120B (high)
- GPT-5.3 Codex (xhigh)
- GPT-5.4 (xhigh)
- GPT-5.4 Pro (xhigh)
Llama 4 Maverick
Gemini 3.1 Pro Preview- Gemini 3 Flash
- Gemini 3.1 Flash-Lite Preview
Claude Opus 4.6 (max)- Claude 4.5 Haiku
- Claude Sonnet 4.6 (max)
Mistral Large 3
DeepSeek V3.2
Grok 4.20 Beta 0309
Nova 2.0 Pro Preview (medium)
MiniMax-M2.7
NVIDIA Nemotron 3 Nano- NVIDIA Nemotron 3 Super
Kimi K2.5
K-EXAONE
MiMo-V2-Pro- MiMo-V2-Flash (Feb 2026)
K2 Think V2
Mi:dm K 2.5 Pro
GLM-5
Qwen3.5 397B A17B
Frequently Asked Questions
Common questions about Sarvam 105B (Reasoning)
Sarvam 105B (Reasoning) was released on March 6, 2026.
Sarvam 105B (Reasoning) was created by Sarvam.
Sarvam 105B (Reasoning) scores 18 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 15).
Sarvam 105B (Reasoning) generates output at 77.9 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight models of similar size (median: 79.3 t/s).
Sarvam 105B (Reasoning) has a time to first token (TTFT) of 2.86s (based on the median across providers serving the model), which is at the higher end compared to other open weight models of similar size (median: 1.44s).
When evaluated on the Intelligence Index, Sarvam 105B (Reasoning) generated 70M output tokens, which is at the higher end compared to other open weight models of similar size (median: 7.4M).
Yes, Sarvam 105B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Sarvam 105B (Reasoning) supports text input.
Sarvam 105B (Reasoning) supports text output.
No, Sarvam 105B (Reasoning) does not support image input. It can only process text.
No, Sarvam 105B (Reasoning) is not multimodal. It only supports text input.
Sarvam 105B (Reasoning) 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 105B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Sarvam 105B (Reasoning) has 106 billion parameters (10.3 billion active).
Sarvam 105B (Reasoning) is a Mixture of Experts (MoE) model with 106 billion total parameters, but only 10.3 billion active parameters are used during inference.
Sarvam 105B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use. View license
Sarvam 105B (Reasoning) achieves a score of 18 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Sarvam 105B (Reasoning) is available via API through 1 provider. Compare API providers
Sarvam 105B (Reasoning) is available through 1 API provider. Compare providers