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-26 Feb 2024
Status
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
28
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atCloudflare Workers AIMistral AI
Input$1.92$0.70
Output$1.92$2.10
Cached input-$0.07
Batch
input / output
--
Cheapest anywhere
input / output
$0.15 / $0.15
Anyscale
$0.70 / $2.10
Mistral 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
$721$311
RAG over documents
2,000 a day, 8K in, 600 out
$992$260
Coding agent
1,000 a day, 40K in, 2K out
$2,423$437
Overnight batch
20,000 a day, 4K in, 400 out
$5,077$2,184
Limits
Context window8K tokens1M tokens
Max output8K tokens1M tokens
Capabilities
Takes inTextText, Images
ProducesTextText
Effort settings
as listed by the source
-low, medium, high
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Assistant prefill