← Brands

Developer: Agnes AI · API distributor: Agnes AI · API model

Current official pay-as-you-go pricing. Mode-specific inputs are mutually constrained: text rejects reference media; keyframe accepts first_frame/last_frame only; reference accepts images/audios/videos and rejects keyframes.

Catalog information only; CreditsPlan does not run inference with this model.

API models and prices · 1

Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.

Agnes Video 2.5

From USD 0.025 / second · mode dependent

Official hosted API: Documented; paid inference not tested

Maximum reference images: 8 · Maximum reference audio clips: 3 · Maximum input video seconds: 12 · Minimum output seconds: 4 · Maximum output seconds: 12

  • text_to_video · 720P
    USD 0.025 / s
    Per request: first 5 reference images included; each extra at standard USD 0.005 / image
    Both input and output video seconds are billed at the resolution rate above.
    Mode-specific inputs are mutually constrained: text rejects reference media; keyframe accepts first_frame/last_frame only; reference accepts images/audios/videos and rejects keyframes. · Pricing source
  • text_to_video · 1080P
    USD 0.04 / s
    Per request: first 5 reference images included; each extra at standard USD 0.005 / image
    Both input and output video seconds are billed at the resolution rate above.
    Mode-specific inputs are mutually constrained: text rejects reference media; keyframe accepts first_frame/last_frame only; reference accepts images/audios/videos and rejects keyframes. · Pricing source
  • text_to_video · 1K
    USD 0.04 / s
    Per request: first 5 reference images included; each extra at standard USD 0.005 / image
    Both input and output video seconds are billed at the resolution rate above.
    Mode-specific inputs are mutually constrained: text rejects reference media; keyframe accepts first_frame/last_frame only; reference accepts images/audios/videos and rejects keyframes. · Pricing source
  • text_to_video · 2K
    USD 0.055 / s
    Per request: first 5 reference images included; each extra at standard USD 0.005 / image
    Both input and output video seconds are billed at the resolution rate above.
    Mode-specific inputs are mutually constrained: text rejects reference media; keyframe accepts first_frame/last_frame only; reference accepts images/audios/videos and rejects keyframes. · Pricing source

Rule version: agnes-official-2026-10-15 · Price verified: 2026-10-15T09:47:52.4934779Z

Estimate image / video cost
References use the dimensions above; only the selected rule applies.

Official model ID: agnes-video-2.5

Input / output: text, image, audio, video → video, audio

Text to video: Supported · keyframeControl: Supported · imageReference: Supported · audioReference: Supported · videoReference: Supported · asynchronous: Supported

Model developer: Agnes AI · Service provider: Agnes AI · Market: com

Model family: Agnes Video 2.5 · Currency: USD

Current official pay-as-you-go pricing.

Requires an official API key; account access, key-type rate limits and applicable subscription quotas apply.

Official source · Last verified: 2026-10-15T09:47:52.4934779Z

Service channels / prices and conditions

No published matching channel quote is available. Check the model status and official sources.

服务渠道 / 价格与条件

暂无可公开的匹配渠道报价,请查看模型状态与官方来源。