Sarvam 105B
sarvam-105bPricing
List prices at Sarvam, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.106 | $0.266 | |
| Cached input 97% off input | $0.00266 | 97% off input |
What it costs a month
At Sarvam list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$42.53
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$35.74
- Coding agent1,000 requests a day, 40K in / 2K out, cached$56.49
- Overnight batch20,000 requests a day, 4K in / 0.4K out$319
Where to run it
1 host serve Sarvam 105B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
SarvamCloud sarvam-105b | $0.106 / $0.266 | sarvam-105b |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Effort settings the source lists
- lowmediumhigh
- Features
- Parallel tool callsPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Sarvam.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 3% less
- 4% less
- 6% less
- 32% less
Call it
Using Sarvam's API.
from litellm import completion
response = completion(
model="sarvam/sarvam-105b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Sarvam 105B cost?
On Sarvam, Sarvam 105B costs $0.106 per million input tokens and $0.266 per million output tokens. Cached input costs $0.00266 per million tokens.
Which APIs offer Sarvam 105B?
Sarvam 105B runs on 1 API: Sarvam.
What is Sarvam 105B's context window?
128K tokens, with up to 128K tokens in one reply.
Is Sarvam 105B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Sarvam 105B?
Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Sarvam 105B's API model id?
Use sarvam-105b with Sarvam.
Sources
Raw catalog entry for sarvam-105b on Sarvam
{
"cache_read_input_token_cost": 2.659574468e-9,
"comment": "These are Sarvam's introductory rates, billed through the end of 2026. Update on 2026-12-31 when the promotion ends. The last published list rates per 1M tokens are INR 15 input, INR 5 cached input and INR 60 output (https://docs.sarvam.ai/changelog/2026/10/10.md).",
"input_cost_per_token": 1.063829787e-7,
"litellm_provider": "sarvam",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.659574468e-7,
"reasoning_effort_levels": [
"low",
"medium",
"high"
],
"source": "https://www.sarvam.ai/token-factory/pricing",
"supports_audio_input": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_video_input": false,
"supports_vision": false
}