Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Anam / Cara

Cara 4 Latest

Experimental rolling Cara 4 channel that follows the latest checkpoint and can change between sessions.

previewClosed weightsVideo generationAudio-driven video
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 18 specification fields collected
Output resolution1152×768 landscape, 768×1152 portraitSee specification notes below
Clip durationNot collectedAwaiting source review
Input billingSee ratesAnam
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Maximum output
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Context caching
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Reasoning
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Tool calling
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Structured output
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Batch processing
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Fine-tuning
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Parameters
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Architecture
Diffusion-based audio-driven visual generationSource for Architecture (opens in a new tab)

Exact parameter count and full architecture are not public in the reviewed sources.

Knowledge cutoff
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Languages
Not collected

No exact model-version contract established; missing information does not mean unsupported.

Release date
2026-05-12Source for Release date (opens in a new tab)

First documented early-access route, not the date of its current rolling checkpoint.

Input modalities
Image, Audio, TextSource for Input modalities (opens in a new tab)

Reference identity and supplied speech drive the visual layer. Cara 4 text controls direct performance; the surrounding LLM and TTS are separate.

Output modalities
VideoSource for Output modalities (opens in a new tab)

Synchronized supplied audio is not proof of native speech generation.

Output resolutions
1152×768 landscape, 768×1152 portraitSource for Output resolutions (opens in a new tab)
Generation controls
Beta Director Notes: preset or custom performance style, expressivity 0–1, and transient inline/data-channel cuesSource for Generation controls (opens in a new tab)

Broad expression guidance, not guaranteed exact poses, gestures or actions.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
cara-4-latest

Rolling experimental channel, not a pinned checkpoint.

Access
POST https://api.anam.ai/v1/auth/session-token with personaConfig.avatarModel=cara-4-latest and a compatible avatarId. Tokens are bound to the supplied configuration and valid for one hour.
Regions
Production inference/media on CoreWeave in Spain/EU and US East. Enterprise can select eu/us engine regions with strict or preferred routing. External providers and stored assets are separate.
Reference image limits
JPEG, PNG or WebP, up to 4.5 MB. Recommended source at least 1152×1152, with margins for landscape/portrait crops.Source for Reference image limits (opens in a new tab)

Source guidance is distinct from output dimensions.

avatarCreation
POST /v1/avatars with an uploaded imageFile or imageUrl, not both. Unlimited saved inventory does not remove daily generation, moderation or capacity limits.Source for avatarCreation (opens in a new tab)
videoControls
Specify videoWidth and videoHeight together. Supported dimensions are 1152×768 and 768×1152; default landscape. Unsupported pairs are rejected. videoQuality selects auto or high initial bitrate.Source for videoControls (opens in a new tab)
performanceStyles
happy, warm, playful, supportive, sad, angry, distressedSource for performanceStyles (opens in a new tab)
performanceCues
Inline cues require speech text; audio passthrough can use director_note_cue messages over the WebRTC data channel. Cues end with the speech turn.Source for performanceCues (opens in a new tab)
transparency
Green background can be removed client-side in WebGL; this is not a native alpha-channel output guarantee.Source for transparency (opens in a new tab)
compatibility
Model access and compatible avatar assets are separate. Explicit unsupported combinations fail instead of falling back. Selecting a model does not migrate or create missing avatar assets.Source for compatibility (opens in a new tab)
channel
Rolling experimental; may change between sessions. All organizations can select it for compatible assets as of October 11, 2026.Source for channel (opens in a new tab)
Billing basis
Billed per second of active session duration, including silence and idling. Monthly included minutes do not roll over. External LLM/TTS charges can be separate for bring-your-own pipelines.Source for Billing basis (opens in a new tab)
sessionLimits
Free 3 minutes; Starter 5; Explorer 10; Growth and Professional 2 hours; Enterprise unlimited under the published plan table. Account agreements and overrides govern.Source for sessionLimits (opens in a new tab)
Concurrent requests
Free/Starter 1; Explorer 3; Growth 5; Professional 10; Enterprise custom, advertised from 100 to unlimited. Shared across the organization.Source for Concurrent requests (opens in a new tab)
subscriptions
Starter $12/month with 50 included minutes; Explorer $49 with 250; Growth $299 with 2,000; Professional $999 with 8,000. Free has 30 and no overage.Source for subscriptions (opens in a new tab)
enterpriseRate
Advertised from $0.04 per minute at scale, subject to negotiated Enterprise terms; not a universal self-serve rate.Source for enterpriseRate (opens in a new tab)
regionalRouting
Enterprise sessionOptions.region: eu or us. Strict routing fails rather than crossing region; preferred routing can fail over. Engine selection does not govern all stored data or external providers.Source for regionalRouting (opens in a new tab)
retentionControls
Enterprise zeroDataRetention applies to session content. Operational infrastructure logs retained 30 days; avatar source images and uploaded knowledge are excluded. Not every LLM/voice supports ZDR.Source for retentionControls (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Session overageStarter session usage1$0.16minute of active session
Session overageExplorer session usage1$0.14minute of active session
Session overageGrowth session usage1$0.12minute of active session
Session overageProfessional session usage1$0.11minute of active session

Rate conditions

  1. Paid plan and included allowance apply. Billed per second; active silence and idle avatar time count. Minutes are aggregate session usage, not additive charges for face/STT/LLM/TTS. External providers can bill separately. Experimental model access and compatible avatar assets must be checked; no token-price conversion.
Pricing source (opens in a new tab)

Data & enterprise terms

Default recordings retained up to 30 days; reports/transcripts/analytics remain until deleted. Enterprise ZDR keeps session content in volatile memory but excludes source avatar images, knowledge files and operational/account metadata. Applicable terms prohibit customer-content training, subject to any separate written agreement described in governance.

Read the service policy (opens in a new tab)

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.

Anam

cara-4-latest
Not verified

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

How it works
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

Minimum reusable input
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

Lifetime & refresh
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

How to enable it
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

Usage fields
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

Billing rules
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

Limits & data boundaries
Not collected

No provider prompt-cache API or model-specific cached tariff has been established. Saved avatars and internal inference state are separate.

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

Anam’s governance page explicitly identifies CARA as proprietary avatar models it develops and owns. Hosted access and open SDKs do not grant access to those model weights.

Classification evidence (opens in a new tab)

Lifecycle dates

Early-access route introduced12 May 2026Source (opens in a new tab)
Access expanded to all organizations with compatible avatars11 Oct 2026Source (opens in a new tab)

Sources reviewed