Personal Workspace
本页内容
快速开始
Hypereal API 提供对强大媒体生成模型的访问。所有请求需要使用您的 API 密钥进行 Bearer 身份验证。
生成一张图像
curl -X POST https://api.hypereal.cloud/v1/images/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a sunset over the ocean",
"model": "gpt-image-2",
"mode": "fast"
}'生成一个视频
curl -X POST https://api.hypereal.cloud/v1/videos/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-2-6-i2v",
"mode": "fast",
"input": {
"prompt": "a cat walking",
"image": "https://example.com/cat.jpg"
}
}'可用模型
qwen3.5-plus
Qwen 3.5 Plus(Alibaba)10% OFF
Input: $0.90/MTok · Output: $5.40/MTok · Context: 128k
qwen3-max
Qwen3 Max(Alibaba)10% OFF
Input: $1.58/MTok · Output: $6.30/MTok · Context: 128k
qwen3.5-flash
Qwen 3.5 Flash(Alibaba)10% OFF
Input: $0.27/MTok · Output: $2.70/MTok · Context: 128k
deepseek-v3.2
DeepSeek V3.2(DeepSeek)10% OFF
Input: $0.90/MTok · Output: $3.60/MTok · Context: 128k
glm-5
GLM-5(Zhipu)10% OFF
Input: $0.90/MTok · Output: $4.05/MTok · Context: 128k
kimi-k2.5
Kimi K2.5(Moonshot)10% OFF
Input: $0.90/MTok · Output: $4.73/MTok · Context: 128k
MiniMax-M2.5
MiniMax M2.5(MiniMax)10% OFF
Input: $0.48/MTok · Output: $1.89/MTok · Context: 128k
gemini-2.0-flash
Gemini 2.0 Flash(Google)10% OFF
Input: $0.09/MTok · Output: $0.36/MTok · Context: 1M
gemini-2.5-flash
Gemini 2.5 Flash(Google)10% OFF
Input: $0.27/MTok · Output: $2.25/MTok · Context: 1M
gemini-2.5-pro
Gemini 2.5 Pro(Google)10% OFF
Input: $1.13/MTok · Output: $9.00/MTok · Context: 1M
gemini-3-flash
Gemini 3 Flash(Google)10% OFF
Input: $0.36/MTok · Output: $2.16/MTok · Context: 1M
gemini-3.1-fast
Gemini 3.1 Fast(Google)10% OFF
Input: $0.63/MTok · Output: $8.64/MTok · Context: 1M
gemini-3.1-pro
Gemini 3.1 Pro(Google)10% OFF
Input: $0.63/MTok · Output: $8.64/MTok · Context: 1M
dolphin
Dolphin (Uncensored)(Venice)
Input: $0.20/MTok · Output: $0.90/MTok · Context: 33k
请求体
model
可选
Model ID from the list above (default: claude-sonnet-4-6)
messages
必填
Array of message objects with
role and contenttemperature
可选
Sampling temperature 0.0-2.0 (default: 0.8)
max_tokens
可选
Maximum tokens to generate (default: 4096)
stream
可选
Enable SSE streaming (default: true)
定价
Pricing varies by model. See the model list above for per-model input/output rates. Credits scale with token usage. See full pricing.
cURL 请求
curl -X POST https://api.hypereal.cloud/v1/chat \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"messages": [
{"role": "user", "content": "Hello, how are you?"}
],
"stream": false
}'Response (200 OK)
{
"id": "chatcmpl-abc123",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! I'm doing great..."
},
"finish_reason": "stop"
}],
"creditsUsed": 2
}JavaScript (Streaming)
const response = await fetch('https://api.hypereal.cloud/v1/chat', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
body: JSON.stringify({
messages: [{ role: 'user', content: 'Hi!' }],
stream: true
})
});
const reader = response.body.getReader();
while (true) {
const { done, value } = await reader.read();
if (done) break;
// Process SSE chunks
}POST
/api/v1/messages新Pay-as-you-go
Anthropic Messages API
Anthropic-compatible /v1/messages endpoint for Claude Code, OpenCode, and any Anthropic SDK client. Supports streaming, tools, and extended thinking.
Billed per token from your credit balance. Not included in subscription plans.
Supported Models
claude-opus-4-6
In: $4.00/MTok · Out: $20.00/MTok
claude-sonnet-4-6
In: $2.40/MTok · Out: $12.00/MTok
claude-haiku-4-5
In: $0.60/MTok · Out: $3.00/MTok
Claude Code Setup
Set these environment variables and launch Claude Code:
export ANTHROPIC_BASE_URL=https://api.hypereal.cloud/api export ANTHROPIC_API_KEY=ck_YOUR_API_KEY claude
curl (streaming)
curl -X POST https://api.hypereal.cloud/api/v1/messages \
-H "Content-Type: application/json" \
-H "x-api-key: ck_YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "claude-sonnet-4-6",
"max_tokens": 1024,
"stream": true,
"messages": [
{"role": "user", "content": "Hello!"}
]
}'Python (Anthropic SDK)
import anthropic
client = anthropic.Anthropic(
base_url="https://api.hypereal.cloud/api",
api_key="ck_YOUR_API_KEY",
)
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)POST
/api/v1/chat/completions新Pay-as-you-go
Chat Completions API
OpenAI-compatible /v1/chat/completions endpoint for Codex CLI, Cursor, Continue, and any OpenAI SDK client. Full support for all GPT-5 and Codex models.
Billed per token from your credit balance. Not included in subscription plans.
Supported Models (selection)
Codex Models — optimized for coding
gpt-5.3-codex
In: $2.50/MTok · Out: $7.50/MTok
gpt-5.3-codex-spark
In: $2.50/MTok · Out: $7.50/MTok
gpt-5.2-codex
In: $2.50/MTok · Out: $7.50/MTok
gpt-5.1-codex
In: $1.25/MTok · Out: $5.00/MTok
gpt-5.1-codex-max
In: $1.25/MTok · Out: $5.00/MTok
gpt-5.1-codex-mini
In: $0.15/MTok · Out: $0.63/MTok
gpt-5-codex
In: $1.25/MTok · Out: $5.00/MTok
gpt-5-codex-mini
In: $0.15/MTok · Out: $0.63/MTok
o-series — reasoning models
o4-mini
In: $0.55/MTok · Out: $2.20/MTok
o3
In: $5.00/MTok · Out: $20.00/MTok
o3-mini
In: $0.55/MTok · Out: $2.20/MTok
o3-pro
In: $10.00/MTok · Out: $40.00/MTok
o1
In: $7.50/MTok · Out: $30.00/MTok
o1-mini
In: $1.50/MTok · Out: $6.00/MTok
GPT-5 family — general purpose
gpt-5
In: $1.25/MTok · Out: $5.00/MTok
gpt-5-pro
In: $2.50/MTok · Out: $7.50/MTok
gpt-5.5
In: $2.50/MTok · Out: $15.00/MTok
gpt-5.4
In: $1.25/MTok · Out: $7.50/MTok
gpt-5.4-mini
In: $0.20/MTok · Out: $1.80/MTok
gpt-5.4-nano
In: $0.05/MTok · Out: $0.48/MTok
56 models supported. All GPT-3.5, GPT-4, GPT-4o, GPT-5 variants included. GET /api/v1/chat/completions for the full model list and pricing.
Codex CLI Setup
Codex CLI speaks OpenAI's Responses API by default. Configure it as a custom provider pointing at /api/v1/responses.
Step 1 — Install
npm install -g @openai/codex # or: brew install codex
Step 2 — Generate an API key at manage-api-keys (must start with ck_)
Step 3 — Write ~/.codex/config.toml
model = "gpt-5-codex" model_provider = "hypereal" [model_providers.hypereal] name = "Hypereal" base_url = "https://hypereal.cloud/api/v1" env_key = "HYPEREAL_API_KEY" wire_api = "responses"
base_url stops at /api/v1.wire_api = "responses" is required.
Step 4 — Export the key (name must match env_key)
export HYPEREAL_API_KEY="ck_your_key_here" # Persist across shells: echo 'export HYPEREAL_API_KEY="ck_your_key_here"' >> ~/.zshrc
Step 5 — Run
codex # or one-shot: codex exec "refactor this function"
Verify
curl https://hypereal.cloud/api/v1/responses
Returns JSON with supported models. If this fails, Codex CLI also cannot connect.
Troubleshooting
- 401 unauthorized: key missing
ck_prefix, or env var empty (echo $HYPEREAL_API_KEYto verify). - missing env HYPEREAL_API_KEY: export it in the shell where you run
codex. - stuck on "connecting":
wire_apimissing or wrong. - MCP client failed to start: harmless warning from a pre-existing MCP config; silence with
mcp_servers = {}. - 402 insufficient credits: top up at settings (min 200 credits).
curl (streaming)
curl -X POST https://api.hypereal.cloud/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ck_YOUR_API_KEY" \
-d '{
"model": "gpt-5",
"stream": true,
"messages": [
{"role": "user", "content": "Hello!"}
]
}'Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://api.hypereal.cloud/api/v1",
api_key="ck_YOUR_API_KEY",
)
response = client.chat.completions.create(
model="gpt-5",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")POST
/api/v1/images/generate生成图像
使用最先进的 AI 模型生成图像。此端点同步处理请求，并在响应中直接返回生成的图像 URL。
请求体
prompt
必填
Text description of the image to generate
model
可选
Model slug (defaults to
gpt-image-2)size
可选
Output resolution (e.g., "1024*1024")
image
可选
Source image URL (for image editing models)
mode
可选
auto (default) or fast. Auto selects the best provider. Fast uses Wavespeed direct (no queue, surcharge applies).响应字段
created
Unix timestamp of when the image was created
data
Array containing the generated image(s) with
url and modelcreditsUsed
Number of credits consumed for this generation
resultId
Unique identifier for the generated result
cURL 请求
curl -X POST https://api.hypereal.cloud/v1/images/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"prompt": "A futuristic cityscape at sunset with flying cars",
"model": "gpt-image-2",
"mode": "fast",
"aspect_ratio": "16:9"
}'Response (200 OK)
{
"created": 1766841456,
"data": [
{
"url": "https://pub-xxx.r2.dev/generated/images/xxx.png",
"model": "gpt-image-2"
}
],
"resultId": "res_abc123456",
"creditsUsed": 4
}POST
/api/v1/videos/generate生成视频
使用最先进的 AI 模型生成视频。此端点支持文本转视频和图像转视频生成，通过 Webhook 回调实现异步交付。
请求体
model
必填
Model slug (e.g.,
veo-3-1-i2v)input.prompt
可选
Text description for video generation
input.image
可选
Source image URL for image-to-video models
input.duration
可选
Video duration in seconds (model-dependent)
webhook_url
可选
URL to receive the result when generation completes
mode
可选
auto (default) or fast. Auto selects the best provider. Fast uses Wavespeed direct (no queue, surcharge applies).响应字段
jobId
Unique job identifier for polling status
outputUrl
Generated video URL (available when complete)
creditsUsed
Number of credits consumed for this generation
cURL 请求
curl -X POST https://api.hypereal.cloud/v1/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "veo-3-1-i2v",
"mode": "fast",
"input": {
"prompt": "Camera slowly pans across the scene",
"image": "https://hypereal.tech/demo-girl.webp",
"duration": 5
},
"webhook_url": "https://your-server.com/webhook"
}'Response (202 Accepted)
{
"jobId": "job_abc123456",
"status": "processing",
"message": "Generation started. Result will be sent to your webhook URL.",
"creditsUsed": 69
}POST
/api/v1/audio/generateNew64+ emotions
Generate Audio
Text-to-speech, voice cloning, and speech recognition. Supports 64+ emotional expressions for natural-sounding speech synthesis.
可用模型
minimax-voice-clone
Clone any voice from an audio sample and generate speech with that voice
minimax-speech-02
Fast text-to-speech synthesis with emotion control and multiple voice options
minimax-music-02
AI music generation with vocals from text prompts and lyrics
audio-tts
High-quality text-to-speech synthesis with natural intonation and multiple output formats
qwen3-tts-flash
Low-latency text-to-speech with 49+ expressive voices, 10 languages, and Chinese dialects. Optimized for real-time conversations.
audio-clone
Clone any voice from an audio sample and generate speech with zero-shot voice cloning
audio-asr
Automatic speech recognition to transcribe audio to text with timestamps
lyria-3-clip
Audio clip generation powered by Google Lyria 3
lyria-3-pro
Professional audio generation powered by Google Lyria 3 Pro
whisper-large-v3
Speech recognition and transcription powered by OpenAI Whisper Large V3
whisper-large-v3-turbo
Fast speech recognition powered by OpenAI Whisper Large V3 Turbo
Emotion Syntax
Wrap emotions in parentheses at the start of text:
(happy) Hello! • (sad) I miss you • (excited)(laughing) Amazing!Text-to-Speech
curl -X POST https://api.hypereal.cloud/api/v1/audio/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "audio-tts",
"input": {
"text": "(happy) Welcome to Hypereal!",
"format": "mp3"
}
}'Voice Clone
{
"model": "audio-clone",
"input": {
"text": "Clone my voice!",
"audio": "https://example.com/voice.mp3"
}
}Speech Recognition Response
{
"success": true,
"text": "Hello, welcome to Hypereal.",
"duration": 2.5,
"segments": [
{"text": "Hello,", "start": 0.0, "end": 0.8},
{"text": "welcome to Hypereal.", "start": 0.9, "end": 2.5}
]
}POST
/api/v1/3d/generateNewGLB output
Generate 3D Models
Convert images or text to 3D models using state-of-the-art AI. Generate high-quality GLB models ready for use in games, AR/VR, and web applications.
可用模型
tripo3d-2-5-i3d
Single image to 3D (Tripo3D V2.5)
tripo3d-multiview-to-3d
4-view images to 3D (front, back, left, right)
hunyuan3d-v2-base
Single image to 3D with 4K textures (Hunyuan3D)
hunyuan3d-v2-multiview
3-view images to 3D, fast ~30s (front, back, left)
meshy6-text-to-3d
Text to 3D with GLB, FBX, OBJ, USDZ output (Meshy6)
meshy6-image-to-3d
Image to 3D with GLB, FBX, OBJ, USDZ output (Meshy6)
tripo3d-h3-1-text-to-3d
Text to 3D with PBR materials (Tripo3D H3.1)
tripo3d-h3-1-image-to-3d
Single image to 3D with PBR materials (Tripo3D H3.1)
tripo3d-h3-1-multiview-to-3d
2-4 multi-view images to 3D with PBR materials (Tripo3D H3.1)
Output Format
All 3D models are returned in GLB format, which is widely supported by 3D viewers, game engines, and web frameworks.
Single Image to 3D
curl -X POST https://api.hypereal.cloud/api/v1/3d/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "hunyuan3d-v2-base",
"input": {
"image": "https://example.com/object.png"
}
}'Multi-View to 3D
{
"model": "tripo3d-multiview-to-3d",
"input": {
"front_image_url": "https://example.com/front.png",
"back_image_url": "https://example.com/back.png",
"left_image_url": "https://example.com/left.png",
"right_image_url": "https://example.com/right.png"
}
}Response
{
"success": true,
"outputUrl": "https://cdn.hypereal.tech/3d/model.glb",
"creditsUsed": 45
}Processing Modes
Synchronous (Images)
The /api/v1/images/generate endpoint processes requests synchronously. The generated image URL is returned directly in the response.
Asynchronous (Videos)
The /api/v1/videos/generate endpoint processes requests asynchronously. Provide a webhook_url to receive results when complete, or poll the job status endpoint.
Webhook Delivery
Provide a webhook_url in your request to receive the result when generation completes. We'll POST the result directly to your server.
Webhook Payload
{
"status": "completed",
"outputUrl": "https://cdn.hypereal.tech/output/video.mp4",
"jobId": "job_abc123456",
"type": "video",
"model": "veo-3-1-i2v",
"creditsUsed": 69
}Example: Node.js Webhook Handler
app.post('/webhook/hypereal', express.json(), (req, res) => {
const { status, outputUrl, jobId, error } = req.body;
if (status === 'completed') {
console.log(`Job ${jobId} completed: ${outputUrl}`);
// Save to database, notify user, etc.
} else if (status === 'failed') {
console.error(`Job ${jobId} failed: ${error}`);
}
// Always return 200 to acknowledge receipt
res.status(200).json({ received: true });
});✓
Return 200 immediately
Process asynchronously if needed, but respond quickly to avoid timeouts.
✓
Handle idempotency
Use jobId to prevent duplicate processing.
GET
/api/v1/jobs/{id}Job Polling
If you can't receive webhooks, use the pollUrl returned in the initial response to check job status until complete.
Query Parameters
model
Model slug used for generation
type
video or imagePoll Request
GET /api/v1/jobs/job_abc123?model=veo-3-1-i2v&type=video
Response (Completed)
{
"status": "completed",
"outputUrl": "https://cdn.hypereal.tech/output/video.mp4",
"jobId": "job_abc123"
}Supported Models
All available models with their parameters and pricing.
Video Generation (62 models)
Image Generation (32 models)
Image Editing (15 models)
Audio Generation (11 models)
3D Model Generation (9 models)
Error Responses
All endpoints return standard HTTP status codes with error details in JSON format.
401
Unauthorized
{
"error": "Unauthorized. Please log in..."
}400
Bad Request
{
"error": "Model is required"
}402
Insufficient Credits
{
"error": "Insufficient credits",
"required": 69,
"available": 10
}404
Not Found
{
"error": "Job not found"
}Rate Limits
Rate limits are enforced per API key on a rolling 1-hour window.
Default Limit1000 requests/hour
Each API key has a default rate limit of 1000 requests per hour. Exceeding returns 429.
Credits
Credits are deducted when you submit a request (before processing). If the generation fails or returns no output, credits are automatically refunded to your account.
LLM Chat
New2+ credits per message
Video Generation
20-150 credits per video
Image Generation
4-25 credits per image
Image Editing
4-14 credits per edit
Audio Generation
107 credits per voice clone
3D Model Generation
45 credits per 3D model