impulse

Embed

Embedding
API id cohere.embed-v4:0
Input / 1M
$0.12
at Amazon Bedrock
Output / 1M
$0.00
at Amazon Bedrock
Context window
128K
tokens
Max output
-
tokens per reply
Hosts
1
4 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.12$0.00

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$36.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$57.60
  • Coding agent1,000 requests a day, 40K in / 2K out$144
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$288
Use your own numbers

Where to run it

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

HostIn / out per 1M
cohere.embed-v4:0
$0.12 / $0.00
Show 3 more listings: regions, snapshots and variants
Amazon Bedrock
eu
eu.cohere.embed-v4:0
$0.12 / $0.00
us
us.cohere.embed-v4:0
$0.12 / $0.00
global
global.cohere.embed-v4:0
$0.12 / $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
Embeddings

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 Amazon Bedrock.

Smaller Cohere models

  • Embed V5.0 Fast
    Cohere · on Cohere
    $0.08 / $0.00
    Has every key capability
    33% less

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/cohere.embed-v4:0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Embed cost?

On Amazon Bedrock, Embed costs $0.12 per million input tokens.

Which APIs offer Embed?

Embed runs on 1 API: Amazon Bedrock.

What is Embed's context window?

128K tokens.

Is Embed being retired?

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

What are cheaper alternatives to Embed?

Models that cost less and keep most of what it can do: Embed V5.0 Fast on Cohere (33% less).

What is Embed's API model id?

Use cohere.embed-v4:0 with Amazon Bedrock.

Sources

Raw catalog entry for cohere.embed-v4:0 on Amazon Bedrock
{
  "input_cost_per_token": 1.2e-7,
  "litellm_provider": "bedrock",
  "max_input_tokens": 128000,
  "mode": "embedding",
  "output_cost_per_token": 0,
  "output_vector_size": 1536,
  "source": "https://aws.amazon.com/bedrock/pricing/",
  "supports_embedding_image_input": true
}