impulse

Compare models

Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.

Clear
Model
Overview
Released-
Status
Current
Open weightsNo
Hosts
APIs you can call it on
1
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atSarvam
Input$0.106
Output$0.266
Cached input$0.00266
Batch
input / output
-
Cheapest anywhere
input / output
$0.106 / $0.266
Sarvam
Monthly bill · at the price above, 30 days, with each workload's cache and batch use
Chat assistant
5,000 a day, 2K in, 500 out
$42.53
RAG over documents
2,000 a day, 8K in, 600 out
$35.74
Coding agent
1,000 a day, 40K in, 2K out
$56.49
Overnight batch
20,000 a day, 4K in, 400 out
$319
Limits
Context window128K tokens
Max output128K tokens
Capabilities
Takes inText
ProducesText
Effort settings
as listed by the source
low, medium, high
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Parallel tool calls