Embed 5 Pro and Fast released
Cohere · Model release
Source confirmed
Data as of October 1, 2026 · How the score is built
CurrentProprietaryNon-Reasoning
Embed 5 Pro
Decision readingEmbed 5 Pro is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Sep 30, 2026 — see all recent releases
Embed 5 Pro will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Pro
Embed 5 FastRadar
Full release historyEmbed 5 Pro release history
Radar confirmed these at the source. Use Embed 5 Pro in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- embed-v5.0-proCohere Embed documentation
- Context window
- 128KCohere Embed documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, imageCohere Embed documentation
- Output modalities
- embeddingCohere Embed documentation
- Parameters
- Not disclosed by the provider
- Availability
- Cohere API · Model Vault · Microsoft Foundry · Amazon SageMaker · Licensed private deploymentCohere Embed 5 launch
- Cloud regions
- Not tracked yet
- Lifecycle
- activeCohere Embed 5 launch
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordCohere Embed 5 launch pricing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Embed 5 Pro, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Embed 5 Pro is a proprietary model with a 128K context window. No explicit reasoning mode is documented in this profile.
Generally available on the Cohere API, Model Vault, Microsoft Foundry, and Amazon SageMaker. Cohere supports licensed private VPC or on-premises deployment with vLLM; the launch does not announce publicly downloadable weights.
This embedding model produces vectors for text, images, or fused inputs. Cohere launch results remain in separate retrieval reports and do not enter text-model rankings.
Embed 5 Pro sits in the Embed 5 family with Embed 5 Fast. The profile has no source-displayable benchmark row yet.
Last updated October 1, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Embed 5 Pro perform overall in AI benchmarks?
Embed 5 Pro does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Which sibling models are related to Embed 5 Pro?
Embed 5 Pro belongs to the Embed 5 family. Related tracked variants include Embed 5 Fast. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Embed 5 Pro have full benchmark coverage on BenchLM?
No. Embed 5 Pro currently has 0 source-displayable rows across 645 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Embed 5 Pro?
Embed 5 Pro has a documented context window of 128K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.