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
Released12 Mar 202518 Nov 2026
Status
Current
in 131 days Leaves Amazon Bedrock on 30 Mar 2027
Current
Open weightsYes, Gemma LicenseNo
Hosts
APIs you can call it on
62
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listedGoogle AI Studio
Input-$3.00
Output-$15.00
Cached input-$0.15
Batch
input / output
-$1.50 / $7.50
Cheapest anywhere
input / output
$0.08 / $0.16
DeepInfra
$3.00 / $15.00
Google AI Studio
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
-$1,769
RAG over documents
2,000 a day, 8K in, 600 out
-$1,296
Coding agent
1,000 a day, 40K in, 2K out
-$2,106
Overnight batch
20,000 a day, 4K in, 400 out
-$5,400
Limits
Context window131K tokens1M tokens
Max output8K tokens1M tokens
Capabilities
Takes inText, ImagesAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
-xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
URL context