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-1 Apr 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
13
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atFireworks AIZ.ai
Input$2.80$1.20
Output$8.80$4.00
Cached input$0.52$0.24
Batch
input / output
--
Cheapest anywhere
input / output
$2.80 / $8.80
Fireworks AI
$0.704 / $3.10
AIHubMix
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
$1,295$574
RAG over documents
2,000 a day, 8K in, 600 out
$1,114$490
Coding agent
1,000 a day, 40K in, 2K out
$1,973$874
Overnight batch
20,000 a day, 4K in, 400 out
$8,832$3,840
Limits
Context window203K tokens200K tokens
Max output131K tokens128K tokens
Capabilities
Takes inTextText, Images
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching