←
Models on OpenRouter62 posts
Models on OpenRouter avatar

Models on OpenRouter

@ModelsOnOR

Every new model on @OpenRouter. Launch announcements, model details, and what to try next. openrouter.ai/models

◷ Joined October 2026▧ 16 Photos and videos
Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·13h

2/ How it works: the audio sets the words and the length of the video. A motion prompt of up to 1,200 characters directs the performance, for example "Leans in toward the lens like sharing a secret. Eyebrows raised, a small giggle, then a small nod." Each clip above shows the motion prompt and the audio script behind it. The clips are HeyGen's own examples.

Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·13h

1/ HeyGen Avatar 6 from @HeyGen is live on OpenRouter. Send one photo or a short reference video plus a speech track. Avatar 6 returns a talking video with lip sync, gestures and expression that follow the audio. 1080p or 2K.

0:41
Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·19h

GPT-6.2 Astra and GPT-6.2 Sol from @OpenAI are live on OpenRouter! Astra sets new eval highs at under a third of GPT-6 Astra's cost per task. Astra at $8/M input and $40/M output, Sol at $2/M input and $10/M output. What each one is for 🧵

Post attachment
Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·19h

1/ Seedance 2.5 Flash from @ByteDanceSeed_ is live on OpenRouter. The faster, lower-cost tier of Seedance 2.5: text-to-video, image-to-video, reference-to-video and video editing, up to 30 seconds at 720p, with audio.

0:08
Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·Nov 16

Wan 3.0 is now 40% off on OpenRouter, and Wan 3.0 Prime is 30% off. @Alibaba_Wan's video models, every resolution, same API. Wan 3.0: $0.03 / $0.06 / $0.12 per second Wan 3.0 Prime: $0.0476 / $0.098 / $0.196 per second (480p / 720p / 1080p)

Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·Nov 16

Hy4 flash from @TencentHunyuan is now live on OpenRouter A faster, cheaper Hy4 with the same 1M context, image input, and optional reasoning. A great fit for agents, coding, and high-volume workloads. 50% off through Nov 30: $0.035/M input, $0.14/M output. openrouter.ai/tencent/hy4-fl…

⚡Meet Hy4 flash, the cheapest model for everyday productivity. Matches Claude Haiku 5.5 (high) on daily work (human blind tests), yet 18x task cost reduction. API pricing (per 1M tokens): $0.003 cached · $0.070 input · $0.281 output. 🔗:hy.tencent.ai/research/hy4-f…

Post attachment
View quoted post ↗
Models on OpenRouter avatar
Models on OpenRouter@ModelsOnOR·Nov 13

Ling 3.2 Flash from inclusionAI is free on OpenRouter for the next 2 weeks. A hybrid reasoning model with a 1M-token context window and text and image input, with up to 200 images per request and a request body up to 30 MB. Try it now: openrouter.ai/inclusionai/li…