Explore AI models on Hedra
video modelFrom 14.85¢/second
Seedance 2.5
Reference-driven video up to 30 seconds at 1080p, with native audio.
New & noteworthy
NewNano Banana 2.1Nano Banana 2 with cleaner text and layouts, and characters that stay consistent across references, up to 4K.image · From 8¢/generation
NewGemini Omni FlashGemini's fast multimodal video model — cinematic clips with native audio from a prompt, a keyframe, or reference images.video · 12.67¢/second
NewWan 3.0Wan 3.0 video with native audio, up to 30 seconds in one shot — from a text prompt, from a first frame with an optional last frame, or from reference images that keep subjects consistentvideo · From 5¢/second
NewKling V3 Motion ControlAnimate a character image to match the motion of a reference video. Standard tier for cost-effective generation.video · From 12.6¢/second
LLMs & VLMs
Reasoning, coding, and multimodal understanding through the API.
DeepSeek V4 Pro 0813Frontier reasoning model, thinking enabled by default. Dated snapshot pinned for reproducible behavior. Text input only.$1.32 per 1M input tokens, $0.132 per 1M cached input tokens, $3.96 per 1M output tokensDeepSeek V4.1 FlashFast, low-cost reasoning model with thinking enabled by default. Multimodal input, short completions.$0.30 per 1M input tokens, $0.007 per 1M cached input tokens, $1.20 per 1M output tokensGLM-5.3Frontier coding and agentic model with configurable thinking effort. Multimodal input.$1.40 per 1M input tokens, $0.14 per 1M cached input tokens, $4.40 per 1M output tokensGLM-5.3 FlashFast, low-cost sibling of GLM-5.3 for high-volume agentic and chat workloads. Multimodal input.$0.15 per 1M input tokens, $0.03 per 1M cached input tokens, $0.50 per 1M output tokensKimi K3Large mixture-of-experts model with native thinking and vision. Built for long-horizon agentic work.$3.00 per 1M input tokens, $0.30 per 1M cached input tokens, $15.00 per 1M output tokens
Explore language modelsAudio
ElevenLabs V3The most expressive ElevenLabs voice — emotional range and delivery cues for performance, not just narration.From 10¢/1,000 charactersElevenLabs Multilingual V2Steady, natural narration across 30+ languages, for finished voiceover.From 10¢/1,000 charactersElevenLabs Flash Multilingual V2The low-latency voice across 30+ languages, for interactive and high-volume speech.From 10¢/2,000 charactersElevenLabs MusicFull tracks from a written brief, with optional lyrics placed across the length you ask for.60¢/minuteElevenLabs Sound EffectsOne-off sound effects from a written description, loopable on request.0.71¢/secondMiniMax Speech-2.5 HD PreviewThe high-fidelity tier — closest voice likeness, across 40+ languages.12.86¢/1,000 characters
See all 12 audio models