impulse

Decision

Other
API id decision
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
32K
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

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

HostIn / out per 1M
decision
-

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

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Independent models

No similar Independent model keeps its key capabilities.

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using Parallel AI's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Decision?

Decision runs on 1 API: Parallel AI.

What is Decision's context window?

32K tokens.

Is Decision being retired?

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

What is Decision's API model id?

Use decision with Parallel AI.

Sources

Raw catalog entry for decision on Parallel AI
{
  "input_cost_per_query": 0.001,
  "input_cost_per_token": 0,
  "output_cost_per_token": 0,
  "litellm_provider": "parallel_ai",
  "max_input_tokens": 32000,
  "mode": "evaluation",
  "source": "https://docs.parallel.ai/getting-started/pricing#decisions-api",
  "supported_endpoints": [
    "/v1/decisions",
    "/v1/systemone"
  ]
}