Request batching is distinct from asynchronous Embed Jobs. Token limits still apply per input.
Embedding controls
input_type: search_document, search_query, classification, clustering or image, truncate: END (default), START or NONE, max_tokens: per-input truncation control, priority: lower values receive higher prioritySource for Embedding controls (opens in a new tab)
These are embedding API controls, not text-generation sampling parameters.
Deployment-specific identifier; do not substitute the Cohere API model selector.
Access
Dedicated model instance. Hourly and monthly commitments are alternative pricing options.
Regions
Not collected
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Dedicated inference · Small
Hourly1
$3.00
instance-hour
Dedicated inference · Small
Monthly1
$2,000.00
instance-month
Dedicated inference · Medium
Hourly2
$5.00
instance-hour
Dedicated inference · Medium
Monthly2
$3,250.00
instance-month
Rate conditions
Small Model Vault performance tier. Per-instance commitment, not an additional per-token API fee. Region, taxes and contract terms require confirmation.
Medium Model Vault performance tier. Per-instance commitment, not an additional per-token API fee. Region, taxes and contract terms require confirmation.
Deployment-specific identifier; do not substitute the Cohere API model selector.
Access
Self-hosting is advertised for VPC/on-premises deployments; commercial access is not a public weight release.
Regions
Not collected
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Cohere API
embed-v5.0-fast
Not verified
No model-specific embedding cache contract verified. A shared API cached_tokens schema field is insufficient evidence of support.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Amazon SageMaker
Not verified
No model-specific embedding cache contract verified. A shared API cached_tokens schema field is insufficient evidence of support.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Microsoft Foundry
Cohere-Embed-V5-Fast
Not verified
No model-specific embedding cache contract verified. A shared API cached_tokens schema field is insufficient evidence of support.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Cohere Model Vault
Not verified
No model-specific embedding cache contract verified. A shared API cached_tokens schema field is insufficient evidence of support.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Cohere private deployment
Not verified
No model-specific embedding cache contract verified. A shared API cached_tokens schema field is insufficient evidence of support.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Classification inference from reviewed distribution: Cohere offers this original model through its API, commercial Model Vault and private deployments; the release does not publish a public weight download. The official model overview distinguishes downloadable families, and reviewed Cohere/CohereLabs embedding repositories do not list Embed 5 weights. This is not an explicit license statement or proof that weights can never be licensed privately.
