HunyuanVideo Text-to-Video API: Endpoint & Pricing
Create short generative video with HunyuanVideo Text-to-Video on LLM.API, with resolution-aware pricing and a unified developer workflow.
What is HunyuanVideo Text-to-Video?
HunyuanVideo Text-to-Video targets motion content rather than chat. Video generation model by Muapi. On LLM.API it sits alongside other media models under a single developer account.
Can you self-host HunyuanVideo Text-to-Video?
No. We found no public weights for HunyuanVideo Text-to-Video on Hugging Face, so there is nothing to download, quantize or serve on your own GPUs: no VRAM budget, no vLLM or GGUF build to plan for. The only way to run it is over an API.
Skip the deploy — use LLM.API as your endpoint
No GPUs, no quantization trade-offs. Same model, OpenAI-compatible, with custom volume discounts on request.
Providers
LLM.API routes HunyuanVideo Text-to-Video to the providers below, with discounted effective rates versus list price.
List price by provider
InputOutputProvider list prices; the LLM.API discount applies on top.
| Provider | Pricing | Context | Capabilities |
|---|---|---|---|
| in —; out $0 per second of video | — | — |
Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 11 Oct 2026.
Try this model
Test HunyuanVideo Text-to-Video right here — free to start.
Suggestions for your first prompt
Code snippet
Call HunyuanVideo Text-to-Video through the OpenAI-compatible API — Video generation via LLM.API (see docs for media endpoints).
Switching from OpenAI? Change 2 lines.
- base_url="https://api.openai.com/v1"
- api_key="YOUR_OPENAI_KEY"
+ base_url="https://api.llmapi.ai/v1"
+ api_key="YOUR_LLMAPI_KEY"Everything else stays the same — SDK, message format, tools, streaming. Set model to hunyuan-t2v and the call runs unchanged.
curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hunyuan-t2v",
"messages": [
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}'from openai import OpenAI
client = OpenAI(
api_key="YOUR_LLMAPI_KEY",
base_url="https://api.llmapi.ai/v1",
)
resp = client.chat.completions.create(
model="hunyuan-t2v",
messages=[
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."},
],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.LLMAPI_KEY,
baseURL: "https://api.llmapi.ai/v1",
});
const resp = await client.chat.completions.create({
model: "hunyuan-t2v",
messages: [
{ role: "user", content: "Give me three crisp launch checklist items." },
],
});
console.log(resp.choices[0].message.content);stream = client.chat.completions.create(
model="hunyuan-t2v",
messages=[{"role": "user", "content": "Write a haiku about latency."}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True){
"model": "hunyuan-t2v",
"messages": [
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}ENDPOINTS
Supported endpoints & features
Base URL https://api.llmapi.ai/v1 · model ID hunyuan-t2v · OpenAI-compatible.
POST /v1/chat/completionsChat Completions — supported
| Feature | Status | How to set it |
|---|---|---|
| Function calling (tools) | Not supported | tools, tool_choice |
| Parallel tool calls | Not supported | parallel_tool_calls |
| JSON mode | Not supported | response_format: {"type": "json_object"} |
| Structured outputs | Not supported | response_format: {"type": "json_schema", …} |
| Streaming | Not supported | stream: true |
| Vision (image input) | Not supported | image_url content parts |
| Web search | Not supported | web_search |
ERRORS
Errors & fallback routing
| Code | What it means | What to do |
|---|---|---|
401 | Missing or invalid API key. | Send Authorization: Bearer YOUR_LLMAPI_KEY and check the key is active. |
429 | Rate limited, or the upstream provider is throttling the request. | Back off and retry with jitter; the gateway also retries the request on another provider where one is available. |
5xx | Upstream provider error or timeout. | Retry; fallback routing sends the retry to the next healthy provider for this model. |
When a provider fails or throttles, the request is routed to the next provider serving this model — the ones listed in the providers table above.
HunyuanVideo Text-to-Video in production
What the model is good at.
Resolution options
Supports multiple output resolutions depending on provider pricing tiers.
Cinematic prompting
Responds to camera, lighting, and mood language in creative briefs. Reflects video generation positioning for this endpoint.
Text-to-video generation
Synthesizes short video clips from prompts for ads, explainers, and social. Tuned to how teams typically call HunyuanVideo Text-to-Video.
Storyboard acceleration
Turns written beats into moving drafts for rapid review. Relevant for `hunyuan-t2v` workloads on LLM.API.
Short-form content
Fits vertical and horizontal short-form marketing formats. Tuned to how teams typically call HunyuanVideo Text-to-Video.
What you get when you call HunyuanVideo Text-to-Video through LLM.API.
Unified AI Routing
Reach HunyuanVideo Text-to-Video and sibling models through one OpenAI-compatible endpoint.
One endpoint, every model.Cost Control
Production: Compare provider price points and keep spend visible as you scale HunyuanVideo Text-to-Video.
More performance, less spend.Reliability Layer
Production: Retry and route across configured providers when a single upstream blips.
Never go dark on users.Observability
Trace prompts, tokens, and errors for HunyuanVideo Text-to-Video alongside the rest of your stack.
See every token, everywhere.Drop-in SDKs
Practical: Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.
Think tasks, not models.Model Breadth
Production: Swap HunyuanVideo Text-to-Video for chat, media, or embedding alternatives without rewriting auth.
Scale from 1 to millions.
When to Use — When NOT to Use
Use it if...
- You can tolerate longer generation times than chat (HunyuanVideo Text-to-Video)
- You are building short-form generative video features (HunyuanVideo Text-to-Video)
- You need resolution-tiered pricing for motion content (HunyuanVideo Text-to-Video)
Avoid if...
- You only need still images or chat text
- You require sub-second interactive generation
- You need broadcast-length films or guaranteed cinema-grade continuity
COMMUNITY
What creators say about AI video models
Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to HunyuanVideo Text-to-Video.
- Creator reviews of the latest Kling releases praise multi-shot consistency, native audio and genuine 4K output.
- Comparisons with Sora and Runway focus on prompt adherence and motion stability rather than raw resolution.
- The common workflow advice: generate many short takes cheaply, then upscale or extend the ones that land.
SOURCES
COMMUNITY
What developers say about HunyuanVideo Text-to-Video
Summarised from public developer discussions and write-ups. Opinions are the sources’, not LLM.API’s.
- Developers on DediRock report that HunyuanVideo stands out for its flexibility and ease of training compared to other open-source models like LTX.
- According to developers at DediRock and Progressive Robot, the model is one of the first open-source frameworks capable of rivaling competitive closed-source models like Sora and Veo-2.
- Contributors on GitHub and Hugging Face highlight the model's high hardware requirements for local deployment, though FP8 weights and xDiT parallel inference are available to optimize GPU memory.
SOURCES
Frequently Asked Questions
How is HunyuanVideo Text-to-Video priced on LLM.API?
Listed pricing metadata shows: $0.03/sec. Confirm live rates in the LLM.API dashboard or docs before production budgeting.
How long do HunyuanVideo Text-to-Video jobs take?
Video generation typically takes longer than chat; latency scales with duration and resolution and may vary by queue.
What modalities does HunyuanVideo Text-to-Video support?
HunyuanVideo Text-to-Video accepts text and produces video according to its architecture metadata on LLM.API.
Where is the canonical page for HunyuanVideo Text-to-Video?
https://llmapi.ai/models/hunyuan-t2v/
What are limitations of HunyuanVideo Text-to-Video?
Like other API models, HunyuanVideo Text-to-Video can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
Which providers serve HunyuanVideo Text-to-Video?
LLM.API currently lists: muapi. Availability can vary by region and account.
Does HunyuanVideo Text-to-Video support streaming?
Streaming depends on the active provider; check the providers table on this page for flags.
What is the context length for HunyuanVideo Text-to-Video?
Reported context for HunyuanVideo Text-to-Video is See provider specs. Always verify the active provider row if multiple providers are listed.
When should I choose HunyuanVideo Text-to-Video?
You can tolerate longer generation times than chat — especially when you specifically need HunyuanVideo Text-to-Video.
Is HunyuanVideo Text-to-Video a chat model?
No—HunyuanVideo Text-to-Video is categorized as a video model. Use the matching API surface rather than assuming chat completions.
COMPARE
Competitive Models
Runway Text-to-Video
Output$0.03 / secondList price per second of video.
— in / $0.03 out per second of video, context varies — the closest current alternative to HunyuanVideo Text-to-Video.
Sora 2 Standard Text-to-Video
Output$0.03 / secondList price per second of video.
— in / $0.03 out per second of video, context varies — the closest current alternative to HunyuanVideo Text-to-Video.
HunyuanVideo Fast Text-to-Video
Output$0.03 / secondList price per second of video.
— in / $0.03 out per second of video, context varies — the closest current alternative to HunyuanVideo Text-to-Video.
Get one key to every model
Swap your API key. Keep your code.