Verified claim · AI-ML · 100% confidence
Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages.
Last verified 2026-05-16 · Methodology veritas-v0.1 · 2f9c856fbdd1a2c7
Structured fields
- Subject
- Cohere Embed v4
- Predicate
publicly_released_on- Object
- 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages
- Confidence
- 100%
- Tags
- embed-v4 · cohere · embeddings · multimodal · rag · released_on · 2025
Sources (2)
[1] official blog · Cohere · 2025-04-09
Embed 4 — Multimodal Embeddings for Enterprise Search and RAG“Embed 4, our latest multimodal embedding model designed to revolutionize how businesses search and retrieve information.”
[2] docs · Cohere · 2025-04-09
Cohere Embed documentation — embed-v4.0
Cite this claim
Ready-to-paste citation (Markdown / plain text):
Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages. — SourceScore Claim 2f9c856fbdd1a2c7 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/2f9c856fbdd1a2c7/" width="100%" height="360" frameborder="0" loading="lazy" title="Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
Llama 4 released on: 2025-04-05 by Meta — Scout + Maverick + Behemoth lineup.
d5ce871dc69e7b04 · 100% confidence · shares 3 tags (multimodal, released_on, 2025)
OpenAI o4-mini publicly released on: 2025-04-16 by OpenAI — successor to o3-mini reasoning model with multimodal input + tool use.
dc1848333261768b · 100% confidence · shares 3 tags (multimodal, released_on, 2025)
Google Gemma 3 publicly released on: 2025-03-12 by Google DeepMind — Gemma 3 family (1B/4B/12B/27B), 128k context, multimodal vision.
a832aaba30ee658e · 100% confidence · shares 3 tags (multimodal, released_on, 2025)
Cohere Command A publicly released on: 2025-03-13 by Cohere — flagship enterprise model with 256k context, agentic workflows focus.
f43580522aad015d · 100% confidence · shares 3 tags (cohere, released_on, 2025)
Cohere Aya Vision publicly released on: 2025-03-04 by Cohere For AI — multilingual open-weight vision-language models (8B + 32B), 23 languages.
e3a0e94cbeffe2c4 · 100% confidence · shares 3 tags (cohere, released_on, 2025)
Frequently asked questions
Is the claim "Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages."?
Evidence comes from 2 primary sources: Cohere, Cohere. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "Cohere Embed v4 publicly released on: 2025-04-09 by Cohere — multimodal embedding model, 256k context support, 100+ languages."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_cohere_embed_v4_fact() -> dict:
"""Fetch the verified SourceScore claim for Cohere Embed v4."""
r = httpx.get("https://sourcescore.org/api/v1/claims/2f9c856fbdd1a2c7.json")
return r.json()