Wan2.2-TI2V-5B-Diffusers
Wan-AI · Kit
Makes video clips from a text prompt or an image plus text, at up to 720P and 24 frames per second, in the Diffusers format for a single consumer GPU.
Wan-AI · Kit
Makes video clips from a text prompt or an image plus text, at up to 720P and 24 frames per second, in the Diffusers format for a single consumer GPU.
Wan-AI · Kit
Generates cinematic video of a character driven by an audio track, and can also lip-sync existing video. For video creators, animators and researchers with a l…
Wan-AI · Kit
Animates a character or swaps one into a video by copying a performer's movement and expressions, as one model from the Wan2.2 video family. Use only faces and…
vllm-sr · Kit
Answers choice, yes-or-no, score, box and tracking questions about text, images or video in one call, with a probability for each answer. For people building r…
About $88.00 at list prices, for 20 sessions a day over 22 days, each reading 80,000 tokens and writing 4,000.
On those numbers, caching the 60% of what each session reads that repeats saves about $37.59 a month. That is after writing it to the cache, which costs more than reading it, as many times a day as you set.
Answers 25% shorter save about $4.40 more, and moving 30% of sessions to Claude Haiku 5.5 saves $12.24. That leaves about $33.77 a month.
Of the 37 text models listed, the cheapest for that month is GPT-6 Luna or Claude Haiku 5.5, about $4.40, and the dearest GPT-6 Astra or Claude Fable 5.1, about $440.00. The compare table lists every one, cheapest first.
On the page’s starting numbers, code adds $39.78 (10 sessions a day on Claude Sonnet 5.5), research $4.00 (20 tasks), pictures $10.60 (100 kept on GPT Image 2 (Square, medium), 2 made for each), video $16.22 (10 clips of 8 seconds on Gemini Omni 1.1 Flash (720p), 2 takes each), voice $0.45 (30 minutes read aloud on OpenAI TTS) and transcription $1.35 (300 minutes on GPT Transcribe). With the text, the month comes to about $160.40.
At list prices, $1 makes about 18 pictures on GPT Image 2 (Square, medium), 9 seconds of video on Gemini Omni 1.1 Flash (720p), 66.6 minutes of speech on OpenAI TTS, or 5 sessions on Claude Sonnet 5.5 (each reading 80,000 tokens and writing 4,000). Each tab’s table shows it for every model.