impulse

Search API

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

Where to run it

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

HostIn / out per 1M
search_api
-

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

Call it

Using Vertex AI's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Search API?

Search API runs on 1 API: Vertex AI.

Is Search API being retired?

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

What is Search API's API model id?

Use search_api with Vertex AI.

Sources

Raw catalog entry for search_api on Vertex AI
{
  "input_cost_per_query": 0.0015,
  "litellm_provider": "vertex_ai",
  "mode": "vector_store"
}