Cohere Embed 5 (Pro + Fast)
Cohere released Embed 5, a multimodal embedding family in two tiers — Pro ($0.12/1M) for max retrieval quality and Fast ($0.08/1M) for latency — sharing one embedding space so teams can index with Pro and query with Fast, with 128K context and 100+ languages.
Why it matters
The shared embedding space is the killer feature: index once with the quality tier, query with the cheap fast tier, no reindexing — a direct cost/latency lever for agentic RAG workloads that issue dozens of searches per task.
What you could build with it
A legal-tech startup could index millions of contracts and filings with Embed 5 Pro once, then serve interactive agent-driven search with the Fast tier, keeping per-query costs low while preserving retrieval quality on visually rich PDFs.
Does it hold up?
Too early to judge — went GA Sept 30 on the Cohere API, Foundry and SageMaker; vendor benchmarks look strong but independent retrieval evaluations have not landed yet.
Built with Cohere Embed 5
- MarkTechPost: Cohere Releases Embed 5 — comparison vs Voyage 4, Gemini Embedding 2, OpenAIMarkTechPost · Benchmark comparison of Embed 5 Pro/Fast against Voyage 4 Large, Gemini Embedding 2 and OpenAI embeddings.
- RuntimeWire: Cohere launches Embed 5 with a cheaper model for live enterprise searchRuntimeWire · Independent take on the shared-space pricing play and the caveat that savings depend on workload.
- HPCwire AIwire: Cohere releases Embed 5 with Pro and Fast tiersHPCwire · Enterprise-angle coverage with the RCP-nDCG@10 methodology detail.
Learn more
First spotted on article: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.