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
Released18 Aug 2026
Status
Older
Newer: GLM 5.3
Open weightsYes, other
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$1.34
Output$4.15
Cached input$0.213
Batch
input / output
-
Cheapest anywhere
input / output
$1.34 / $4.15
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
$612
RAG over documents
2,000 a day, 8K in, 600 out
$522
Coding agent
1,000 a day, 40K in, 2K out
$910
Overnight batch
20,000 a day, 4K in, 400 out
$4,213
Limits
Context window1M tokens
Max output1M tokens
Capabilities
Takes inText
ProducesText
Effort settings
as listed by the source
low, high, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Parallel tool calls