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 weightsYes, Apache-2.0
Hosts
APIs you can call it on
2
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atFireworks AI
Input$3.00
Output$3.00
Cached input-
Batch
input / output
-
Cheapest anywhere
input / output
$3.00 / $3.00
Fireworks AI
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
$1,125
RAG over documents
2,000 a day, 8K in, 600 out
$1,548
Coding agent
1,000 a day, 40K in, 2K out
$3,780
Overnight batch
20,000 a day, 4K in, 400 out
$7,920
Limits
Context window33K tokens
Max output33K tokens
Capabilities
Takes inText
ProducesText
Effort settings
as listed by the source
-
Streaming
JSON mode
Structured outputs