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
Released23 Jan 20269 Nov 2026
Status
Older
Newer: Qwen4 Max
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
57
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listedAnthropic
Input-$8.00
Output-$40.00
Cached input-$0.20
Batch
input / output
-$4.00 / $20.00
Cheapest anywhere
input / output
$1.20 / $6.00
DeepInfra
$8.00 / $40.00
Anthropic
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
-$4,698
RAG over documents
2,000 a day, 8K in, 600 out
-$3,408
Coding agent
1,000 a day, 40K in, 2K out
-$5,448
Overnight batch
20,000 a day, 4K in, 400 out
-$14,400
Limits
Context window258K tokens1M tokens
Max output66K tokens128K tokens
Capabilities
Takes inTextText, Images, 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
Adaptive thinking
Always reasons
Built-in web search
Computer use
Fast mode
Native structured output