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-17 Nov 2026
Status
Older
Newer: Claude 2.1
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 atAmazon BedrockOpenAI
Input$8.00$2.00
Output$24.00$10.00
Cached input-$0.10
Batch
input / output
-$1.00 / $5.00
Long prompts
input / output
-$4.00 / $15.00
above 272K
Cheapest anywhere
input / output
$8.00 / $24.00
Amazon Bedrock
$2.00 / $10.00
OpenAI
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
$4,200$1,179
RAG over documents
2,000 a day, 8K in, 600 out
$4,704$864
Coding agent
1,000 a day, 40K in, 2K out
$11,040$1,404
Overnight batch
20,000 a day, 4K in, 400 out
$24,960$3,600
Limits
Context window100K tokens922K tokens
Max output8K tokens128K tokens
Capabilities
Takes inTextImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
-xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
Tool search