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
Current
Open weightsNoNo
Hosts
APIs you can call it on
11
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockMistral AI
Input$2.00$1.40
Output$6.00$4.40
Cached input-$0.14
Batch
input / output
--
Cheapest anywhere
input / output
$2.00 / $6.00
Amazon Bedrock
$1.40 / $4.40
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
$1,050$637
RAG over documents
2,000 a day, 8K in, 600 out
$1,176$528
Coding agent
1,000 a day, 40K in, 2K out
$2,760$886
Overnight batch
20,000 a day, 4K in, 400 out
$6,240$4,416
Limits
Context window128K tokens1M tokens
Max output16K tokens131K tokens
Capabilities
Takes inTextText
ProducesTextText
Effort settings
as listed by the source
-low, high, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Assistant prefill