impulse

Compress

API id compress
Input / 1M
$0.05
at ScaleDown
Output / 1M
$0.00
at ScaleDown
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at ScaleDown, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.05$0.00

What it costs a month

At ScaleDown list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$15.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$24.00
  • Coding agent1,000 requests a day, 40K in / 2K out$60.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$120
Use your own numbers

Where to run it

1 host serve Compress. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
compress
$0.05 / $0.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than ScaleDown.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using ScaleDown's API.

Python
from litellm import completion

response = completion(
    model="scaledown/compress",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Compress cost?

On ScaleDown, Compress costs $0.05 per million input tokens.

Which APIs offer Compress?

Compress runs on 1 API: ScaleDown.

Is Compress being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Compress?

Models that cost less and keep most of what it can do: Llama 3.2 11B Vision Instruct on DeepInfra (2% less).

What is Compress's API model id?

Use compress with ScaleDown.

Sources

Raw catalog entry for compress on ScaleDown
{
  "input_cost_per_token": 5e-8,
  "output_cost_per_token": 0,
  "litellm_provider": "scaledown",
  "mode": "chat",
  "supports_system_messages": true,
  "supports_function_calling": false,
  "supports_vision": false
}