impulse

Embed Multilingual Light V3.0

Embedding
API id embed-multilingual-light-v3.0
Input / 1M
$100.00
at Cohere
Output / 1M
$0.00
at Cohere
Context window
512
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at Cohere, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$100.00$0.00

What it costs a month

At Cohere list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$30,000
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$48,000
  • Coding agent1,000 requests a day, 40K in / 2K out$120,000
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$240,000
Use your own numbers

Where to run it

2 hosts serve Embed Multilingual Light V3.0. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
CohereLab API
embed-multilingual-light-v3.0
$100.00 / $0.00
cohere.embed-multilingual-light-v3.0
$0.10 / $0.00
−100% vs headline

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

  • Oracle OCI
    cohere.embed-multilingual-light-v3.0
    $0.10 / $0.00
    100% less

Smaller Cohere models

  • Embed V4.0
    Cohere · on Cohere
    $0.12 / $0.00
    Has every key capability
    100% less
  • Embed V5.0 Pro
    Cohere · on Cohere
    $0.12 / $0.00
    Has every key capability
    100% less
  • Embed English Light V3.0
    Cohere · on Cohere
    $0.10 / $0.00
    Has every key capability
    100% less

Other frontier labs

Open-weight picks

Call it

Using Cohere's API.

Python
from litellm import completion

response = completion(
    model="cohere/embed-multilingual-light-v3.0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Embed Multilingual Light V3.0 cost?

On Cohere, Embed Multilingual Light V3.0 costs $100.00 per million input tokens. The cheapest host is Oracle OCI, at $0.10 per million input tokens.

Which APIs offer Embed Multilingual Light V3.0?

Embed Multilingual Light V3.0 runs on 2 APIs: Cohere and Oracle OCI.

What is Embed Multilingual Light V3.0's context window?

512 tokens.

Is Embed Multilingual Light V3.0 being retired?

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

What are cheaper alternatives to Embed Multilingual Light V3.0?

Models that cost less and keep most of what it can do: Embed V4.0 on Cohere (100% less), Gemini Embedding 2 on Google AI Studio (100% less), Text Embedding 3 Large on OpenAI (100% less) and Tongyi Embedding Vision Flash on EmpirioLabs AI (100% less). Embed Multilingual Light V3.0 itself costs 100% less on Oracle OCI.

What is Embed Multilingual Light V3.0's API model id?

Use embed-multilingual-light-v3.0 with Cohere. Other hosts use their own ids: cohere.embed-multilingual-light-v3.0 on Oracle OCI.

Sources

Raw catalog entry for embed-multilingual-light-v3.0 on Cohere
{
  "input_cost_per_token": 0.0001,
  "litellm_provider": "cohere",
  "max_input_tokens": 512,
  "mode": "embedding",
  "output_cost_per_token": 0,
  "supports_embedding_image_input": true
}