{"data":[{"id":"heygen/heygen-avatar-6-turbo","canonical_slug":"heygen/heygen-avatar-6-turbo-20261117","hugging_face_id":null,"name":"HeyGen: Avatar 6 Turbo","created":1794940883,"description":"HeyGen: Avatar 6 Turbo is the faster, lower-cost variant of HeyGen's Avatar 6 avatar video model. It turns a single photo, a short reference video, or both into a lip-synced...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/heygen-avatar-6-turbo-20261117/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"heygen/heygen-avatar-6","canonical_slug":"heygen/heygen-avatar-6-20261117","hugging_face_id":null,"name":"HeyGen: Avatar 6","created":1794940882,"description":"HeyGen: Avatar 6 is HeyGen's avatar video model for turning a single photo, a short reference video, or both into an expressive, lip-synced talking video driven by a supplied audio...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/heygen-avatar-6-20261117/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"bytedance/seedance-2.5-flash","canonical_slug":"bytedance/seedance-2.5-flash-20261115","hugging_face_id":null,"name":"ByteDance: Seedance 2.5 Flash","created":1794874901,"description":"Seedance 2.5 Flash is a video generation model from ByteDance, the faster and lower-cost tier of Seedance 2.5. It supports text-to-video, image-to-video with first-frame and first-and-last-frame control, multimodal reference-to-video, video...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.5-flash-20261115/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"google/gemini-omni-1.2-flash","canonical_slug":"google/gemini-omni-1.2-flash-20261105","hugging_face_id":null,"name":"Google: Gemini Omni 1.2 Flash","created":1793898961,"description":"Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...","context_length":131072,"architecture":{"modality":"text+image+video->text+video","input_modalities":["text","image","video"],"output_modalities":["text","video"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.000009","web_search":"0.014"},"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-omni-1.2-flash-20261105/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses","/api/v1/videos"],"reasoning":{"mandatory":true,"supported_efforts":["high","low"],"default_effort":"low"}},{"id":"google/gemini-omni-1.1-flash","canonical_slug":"google/gemini-omni-1.1-flash-20260911","hugging_face_id":null,"name":"Google: Gemini Omni 1.1 Flash","created":1793825668,"description":"Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...","context_length":131072,"architecture":{"modality":"text+image+video->text+video","input_modalities":["text","image","video"],"output_modalities":["text","video"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000015","completion":"0.000009","web_search":"0.014"},"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-omni-1.1-flash-20260911/endpoints"},"endpoints":["/api/v1/chat/completions","/api/v1/completions","/api/v1/messages","/api/v1/responses","/api/v1/videos"],"reasoning":{"mandatory":true,"supported_efforts":["high","low"],"default_effort":"low"}},{"id":"tbc/mischief-1","canonical_slug":"tbc/mischief-1-20261023","hugging_face_id":null,"name":"TBC: mischief 1","created":1793319378,"description":"TBC mischief 1 is the world's first neuron-derived video model from The Biological Computing Co. It supports image to video and is a fast and affordable way to bring ideas...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/tbc/mischief-1-20261023/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"x-ai/grok-imagine-video-1.5-lite","canonical_slug":"x-ai/grok-imagine-video-1.5-lite-20261001","hugging_face_id":null,"name":"SpaceXSI: Grok Imagine Video 1.5 Lite","created":1791309778,"description":"Grok Imagine Video 1.5 Lite is a faster, lower-cost video generation model from SpaceXSI, distilled from [Grok Imagine Video 1.5](/x-ai/grok-imagine-video-1.5). It supports text-to-video and image-to-video, trading some quality for speed...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-video-1.5-lite-20261001/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"heygen/heygen-video-1","canonical_slug":"heygen/heygen-video-1-20260930","hugging_face_id":null,"name":"HeyGen: HeyGen Video","created":1790798684,"description":"HeyGen Video is a general-purpose video generation model from HeyGen. It renders short clips with synthesized audio (dialogue, ambience, and sound effects) in a single call, working from a text...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/heygen-video-1-20260930/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"black-forest-labs/flux-video-edit","canonical_slug":"black-forest-labs/flux-video-edit-20260910","hugging_face_id":null,"name":"Black Forest Labs: FLUX Video Edit","created":1789073532,"description":"FLUX Video Edit [fast] takes a source video and an edit prompt and returns a precisely edited video. Add, remove, or replace objects and characters, rebuild the setting, edit on-screen...","context_length":0,"architecture":{"modality":"text+video->video","input_modalities":["text","video"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/black-forest-labs/flux-video-edit-20260910/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"minimax/hailuo-3-max","canonical_slug":"minimax/hailuo-3-max-20260901","hugging_face_id":null,"name":"MiniMax: H3 Max","created":1788313310,"description":"MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/hailuo-3-max-20260901/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"alibaba/wan-3.0-prime","canonical_slug":"alibaba/wan-3.0-prime-20260827","hugging_face_id":null,"name":"Alibaba: Wan 3.0 Prime","created":1787863800,"description":"Wan 3.0 Prime is a fast-mode variant of [Wan 3.0](https://openrouter.ai/alibaba/wan-3.0) from Alibaba. It supports text-to-video and first-frame image-to-video generation.","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/alibaba/wan-3.0-prime-20260827/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"alibaba/wan-3.0","canonical_slug":"alibaba/wan-3.0-20260824","hugging_face_id":null,"name":"Alibaba: Wan 3.0","created":1787603856,"description":"Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation. It produces 480p, 720p, or 1080p video with durations from 2 to 30 seconds.","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/alibaba/wan-3.0-20260824/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"heygen/avatar-iv","canonical_slug":"heygen/avatar-iv-20260625","hugging_face_id":null,"name":"HeyGen: Avatar IV","created":1787595728,"description":"HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video. Rather than only matching mouth shapes to words, it interprets the vocal...","context_length":0,"architecture":{"modality":"text+image+audio->video","input_modalities":["text","image","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/avatar-iv-20260625/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"black-forest-labs/flux-video-upscale","canonical_slug":"black-forest-labs/flux-video-upscale-20260819","hugging_face_id":null,"name":"Black Forest Labs: FLUX Video Upscale","created":1787173919,"description":"FLUX Video Upscale is a video upscaling model from Black Forest Labs. It enlarges a single source video by 1.5× to 3× while preserving its duration, with an optional prompt...","context_length":0,"architecture":{"modality":"text+video->video","input_modalities":["text","video"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/black-forest-labs/flux-video-upscale-20260819/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"bytedance/seedance-2.0-mini","canonical_slug":"bytedance/seedance-2.0-mini-20260811","hugging_face_id":null,"name":"ByteDance: Seedance 2.0 Mini","created":1786552600,"description":"Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.0-mini-20260811/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"bytedance/seedance-2.5","canonical_slug":"bytedance/seedance-2.5-20260807","hugging_face_id":null,"name":"ByteDance: Seedance 2.5","created":1786141253,"description":"Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.5-20260807/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"black-forest-labs/flux-3-video","canonical_slug":"black-forest-labs/flux-3-video-20260804","hugging_face_id":null,"name":"Black Forest Labs: FLUX 3 Video","created":1785858831,"description":"FLUX.3 Video is a video generation model from Black Forest Labs. It supports text-to-video, image-guided generation with opening and closing keyframes, and video continuation workflows, making it suited for controlled...","context_length":0,"architecture":{"modality":"text+image+video->video","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/black-forest-labs/flux-3-video-20260804/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"minimax/hailuo-3","canonical_slug":"minimax/hailuo-03-20260730","hugging_face_id":null,"name":"MiniMax: H3","created":1785366648,"description":"MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/hailuo-03-20260730/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"runway/aleph-2","canonical_slug":"runway/aleph-2-20260729","hugging_face_id":null,"name":"Runway: Aleph 2.0","created":1785339484,"description":"Runway Aleph 2.0 is an in-context video editing model from Runway. It applies text instructions and keyframe-guided edits across existing footage while preserving details that are not meant to change....","context_length":0,"architecture":{"modality":"text+image+video->video","input_modalities":["text","image","video"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/runway/aleph-2-20260729/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"runway/gen-4.5","canonical_slug":"runway/gen-4.5-20260729","hugging_face_id":null,"name":"Runway: Gen-4.5","created":1785339483,"description":"Runway Gen-4.5 is a video generation model from Runway for text-to-video and image-to-video workflows. It is designed for cinematic scene creation with strong motion quality, visual fidelity, and prompt adherence....","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/runway/gen-4.5-20260729/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"x-ai/grok-imagine-video-1.5","canonical_slug":"x-ai/grok-imagine-video-1.5-20260719","hugging_face_id":null,"name":"SpaceXSI: Grok Imagine Video 1.5","created":1784548100,"description":"Grok Imagine Video 1.5 is a video generation model from SpaceXSI. It creates videos from text prompts, with an optional starting image to guide the scene. It can direct subject...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","top_logprobs","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-video-1.5-20260719/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"alibaba/happyhorse-1.1","canonical_slug":"alibaba/happyhorse-1.1-20260624","hugging_face_id":null,"name":"Alibaba: HappyHorse 1.1","created":1782269643,"description":"HappyHorse 1.1 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/alibaba/happyhorse-1.1-20260624/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"alibaba/happyhorse-1.0","canonical_slug":"alibaba/happyhorse-1.0-20260624","hugging_face_id":null,"name":"Alibaba: HappyHorse 1.0","created":1782260324,"description":"HappyHorse 1.0 is a video generation model from Alibaba. It generates short videos from a text prompt, a single starting image, or a set of reference images, with output up...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","presence_penalty","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/alibaba/happyhorse-1.0-20260624/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"x-ai/grok-imagine-video","canonical_slug":"x-ai/grok-imagine-video-20260512","hugging_face_id":null,"name":"SpaceXSI: Grok Imagine Video","created":1779117586,"description":"Grok Imagine Video is SpaceXSI's fast, text-, image-, and reference-conditioned video generation model. It produces short videos (1–15 seconds, 24 fps) at 480p or 720p across seven aspect ratios -...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-video-20260512/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"google/veo-3.1-fast","canonical_slug":"google/veo-3.1-fast-20260320","hugging_face_id":null,"name":"Google: Veo 3.1 Fast","created":1776994666,"description":"Google's mid-tier video generation model balancing speed and quality. Veo 3.1 Fast generates high-quality video from text or image prompts with native synchronized audio, offering faster turnaround than Veo 3.1...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/veo-3.1-fast-20260320/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"google/veo-3.1-lite","canonical_slug":"google/veo-3.1-lite-20260331","hugging_face_id":null,"name":"Google: Veo 3.1 Lite","created":1776978818,"description":"Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synchronized audio...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/veo-3.1-lite-20260331/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"minimax/hailuo-2.3","canonical_slug":"minimax/hailuo-2.3-20260420","hugging_face_id":null,"name":"MiniMax: Hailuo 2.3","created":1776702740,"description":"Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows. It is...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/hailuo-2.3-20260420/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"bytedance/seedance-2.0","canonical_slug":"bytedance/seedance-2.0-20260414","hugging_face_id":null,"name":"ByteDance: Seedance 2.0","created":1776211362,"description":"Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency,...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.0-20260414/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"bytedance/seedance-2.0-fast","canonical_slug":"bytedance/seedance-2.0-fast-20260414","hugging_face_id":null,"name":"ByteDance: Seedance 2.0 Fast","created":1776211362,"description":"Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost...","context_length":0,"architecture":{"modality":"text+image+audio+video->video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.0-fast-20260414/endpoints"},"endpoints":["/api/v1/videos"]},{"id":"google/veo-3.1","canonical_slug":"google/veo-3.1-20260320","hugging_face_id":null,"name":"Google: Veo 3.1","created":1774277148,"description":"Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio —...","context_length":0,"architecture":{"modality":"text+image->video","input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/veo-3.1-20260320/endpoints"},"endpoints":["/api/v1/videos"]}],"total_count":30,"links":{"next":null}}