impulse

Nimble

Other
API id nimble
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
8K
tokens
Max output
-
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Where to run it

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

HostIn / out per 1M
nimble
-
Show 1 more listings: regions, snapshots and variants
Bespoke Nimble
Alias
nimble-latest
-

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 Bespoke Nimble's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Nimble?

Nimble runs on 1 API: Bespoke Nimble.

What is Nimble's context window?

8K tokens.

Is Nimble being retired?

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

What is Nimble's API model id?

Use nimble with Bespoke Nimble.

Sources

Raw catalog entry for nimble on Bespoke Nimble
{
  "input_cost_per_token": 0,
  "litellm_provider": "bespoke",
  "max_input_tokens": 8192,
  "mode": "evaluation",
  "output_cost_per_token": 0,
  "source": "https://ollama.com/library/nimble",
  "supported_endpoints": [
    "/v1/systemone"
  ],
  "metadata": {
    "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately"
  }
}