HOUJIAYAN API

Global AI API Gateway

One API, 11+ Chinese AI models.

OpenAI-compatible endpoints for DeepSeek, Qwen, GLM, MiniMax, and Doubao. Self-serve signup, 10,000 free tokens, transparent pricing. Built in Hohhot, powered by Inner Mongolia's renewable grid.

Create free account → Browse models
🎁 10,000 free tokens · 5 req/min · 100 req/day · email verification
11+
Models from 5 vendors
¥1.10 / ~$0.15
Starting price / 1M input
99%
Uptime target
60s
Signup to first call

Models that work for your stack

Flagship reasoning, balanced chat, vision, code, and OCR — all on one OpenAI-compatible endpoint. Switch with a single parameter change.

DeepSeek
deepseek-v4-pro
Flagship reasoning model. 256K context. Top-tier performance on complex analysis, coding, and research.
¥4.38 (~$0.60) in ¥8.76 (~$1.20) out
per 1M tokens
DeepSeek
deepseek-v4-flash
Fast & cost-effective reasoning. 1M context. Ideal for chatbots, content generation, and quick Q&A at scale.
¥1.10 (~$0.15) in ¥2.19 (~$0.30) out
per 1M tokens
Alibaba Cloud
qwen3.7-max
Alibaba's flagship Qwen. 256K context. Balanced performance for general-purpose tasks, translation, and summarization.
¥6.13 (~$0.84) in ¥12.26 (~$1.68) out
per 1M tokens
Alibaba Cloud
qwen3.7-plus
Enhanced Qwen with advanced reasoning and code generation. Great for programming, technical writing, and analysis.
¥6.13 (~$0.84) in ¥12.26 (~$1.68) out
per 1M tokens
Alibaba Cloud
qwen3.5-ocr
Specialized OCR for document text extraction and image understanding. Receipts, contracts, scanned forms.
¥3.65 (~$0.50) in ¥7.30 (~$1.00) out
per 1M tokens
Alibaba Cloud
qwen3.5-livetranslate
Real-time speech translation for live conversation. Meeting transcription, voice apps, simultaneous interpretation.
¥7.30 (~$1.00) in ¥14.60 (~$2.00) out
per 1M tokens
MiniMax
MiniMax-M3
Flagship multimodal model with state-of-the-art capabilities. Vision + text + extended context for advanced agents.
¥15.33 (~$2.10) in ¥61.32 (~$8.40) out
per 1M tokens
MiniMax
MiniMax-M2.7
Advanced model with tool calling and extended reasoning. Agent systems, multi-step planning, function execution.
¥8.76 (~$1.20) in ¥35.04 (~$4.80) out
per 1M tokens
MiniMax
MiniMax-M2.5-highspeed
High-speed variant with 1M token context. Long document specialist — books, codebases, RAG corpora.
¥6.57 (~$0.90) in ¥26.28 (~$3.60) out
per 1M tokens
ByteDance
doubao-seed-code
ByteDance's code generation specialist. Optimized for completion, debugging, and technical documentation.
¥1.46 (~$0.20) in ¥2.92 (~$0.40) out
per 1M tokens
More coming
GLM · Kimi · Step
We're adding Zhipu GLM, Moonshot Kimi, and Step models in the next release. Existing customers get early access.
Q3 2026

Start with 10K free tokens →

Pricing that doesn't pretend

Three plans, no monthly minimum, no per-seat fee. Pay only for what you use. WeChat Pay & Alipay top-up available — email us to set up.

Free
¥0 / 7 days
Try all 11 models. No credit card.
  • 100,000 free credits
  • All 11 models included
  • 5 requests / minute
  • 100 requests / day
  • Email support (48h response)
Start free →
Most popular
Pay-as-you-go
¥1.10 / ~$0.15 · 1M tokens
Buy credits with a redemption code, use them anytime.
  • Buy credits from ¥73 / ~$10 (100K credits)
  • No expiry while account is active
  • 60 requests / minute
  • 100K tokens / minute
  • Streaming, function calling, vision
  • Email support (24h response)
Buy credits →
Volume
Custom
For 100M+ tokens/month, multi-seat, or production SLAs.
  • Volume discount (up to 40% off PAYG)
  • Higher rate limits (negotiated)
  • 99.9% uptime SLA + 4-hour remedies
  • Dedicated channel / multi-key pool
  • Quarterly invoicing, NET-30
  • Direct technical support (1h response)
Contact sales →

Per-model pricing (DeepSeek / Qwen / MiniMax / Doubao) on the table below. International prices from public vendor pages.

Model Input / 1M Output / 1M vs. Intl. equivalent
deepseek-v4-flash ¥1.10 / ~$0.15 ¥2.19 / ~$0.30 vs. GPT-5.4-nano: 33%
deepseek-v4-pro ¥4.38 / ~$0.60 ¥8.76 / ~$1.20 vs. GPT-5.4: 76% / 92%
qwen3.7-max ¥6.13 / ~$0.84 ¥12.26 / ~$1.68 vs. Claude Sonnet 4.6: 72% / 89%
qwen3.7-plus ¥6.13 / ~$0.84 ¥12.26 / ~$1.68 vs. Gemini 2.5 Flash: 60% / 90%
MiniMax-M3 ¥15.33 / ~$2.10 ¥61.32 / ~$8.40 vs. Claude Sonnet 4.6: 30% / 44%
MiniMax-M2.7 ¥8.76 / ~$1.20 ¥35.04 / ~$4.80 vs. Claude Haiku 4.5: -20% / 4%
MiniMax-M2.5-highspeed ¥6.57 / ~$0.90 ¥26.28 / ~$3.60 vs. Gemini 2.5 Flash: 28% / 28%
doubao-seed-code ¥1.46 / ~$0.20 ¥2.92 / ~$0.40 vs. GPT-5.4-nano: 0% / 68%

International prices from public vendor pages. Real-time comparison: api.houjiayan.com/pricing

Free tier — what you get

  • 10,000 tokens credited on signup, valid for the lifetime of the account
  • 5 requests / minute and 100 requests / day — keeps the free tier fast for everyone
  • Need higher limits? Top up to remove the cap, no monthly minimum.

Get started in three steps

No credit card. Email verification required. Sign up, verify, get an API key, and make your first call in under a minute.

1

Create your free account

Self-serve signup. Email + password + a 6-digit code we email you.

Sign up →
2

Generate an API key

Open the console and click "Create new key." 10,000 free tokens are credited automatically.

sk-hj-xxxxxxxxxxxxxxxx
3

Make your first call

OpenAI-compatible. Drop in your existing SDK and change the base URL.

curl https://api.houjiayan.com/v1/chat/completions \
  -H "Authorization: Bearer $HOUJIAYAN_KEY" \
  -d '{"model":"deepseek-v4-flash",...}'

Why teams pick HOUJIAYAN

Five reasons developers switch from direct upstream or other aggregators.

One integration

11 models, 5 vendors, one OpenAI-compatible endpoint. Change models with a single parameter.

Smart failover

Multi-channel routing per model. If upstream is slow or errors, we auto-failover to a backup key.

Renewable-powered

Compute runs on Inner Mongolia's wind + solar grid. Lower carbon than most European data centers.

99% uptime target

Live status page at status.houjiayan.com. Public 30-day rolling uptime for every component.

Transparent billing

Per-token, per-request. View real-time usage in the console. Export CSV anytime.

Privacy by design

We do not log prompts or responses. Single first-party cookie, no analytics, no tracking pixels.

Stop juggling 5 API keys.

One account, 11 models, transparent pricing. 10,000 free tokens the moment your email is verified.

Create free account →