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
Older
in 131 days Leaves Amazon Bedrock (except US government regions) on 30 Mar 2027
Current
Open weightsYes, Llama Community LicenseNo
Hosts
APIs you can call it on
31
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockMeta Model API
Input$0.30$0.10
Output$0.60$0.50
Cached input-$0.004
Batch
input / output
--
Long prompts
input / output
-$0.30 / $1.50
above 200K
Cheapest anywhere
input / output
$0.20 / $0.20
GradientAI
$0.10 / $0.50
Meta Model API
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
$135$58.86
RAG over documents
2,000 a day, 8K in, 600 out
$166$42.96
Coding agent
1,000 a day, 40K in, 2K out
$396$69.36
Overnight batch
20,000 a day, 4K in, 400 out
$864$360
Limits
Context window8K tokens1M tokens
Max output8K tokens524K tokens
Capabilities
Takes inTextAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
-minimal, xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Built-in web search
Parallel tool calls