impulse

Embed Qa 4

Embedding
API id embed-qa-4
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 Embed Qa 4. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NVIDIA NIMInference
embed-qa-4
-

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
Embeddings

Similar models

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

Smaller Cohere models

Other frontier labs

Open-weight picks

Call it

Using NVIDIA NIM's API.

Python
from litellm import completion

response = completion(
    model="nvidia_nim/embed-qa-4",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Embed Qa 4?

Embed Qa 4 runs on 1 API: NVIDIA NIM.

Is Embed Qa 4 being retired?

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

What is Embed Qa 4's API model id?

Use embed-qa-4 with NVIDIA NIM.

Sources

Raw catalog entry for embed-qa-4 on NVIDIA NIM
{
  "litellm_provider": "nvidia_nim",
  "mode": "embedding",
  "source": "https://build.nvidia.com/nvidia/embed-qa-4.md",
  "supported_endpoints": [
    "/v1/embeddings"
  ]
}