https://aicraftapi.com/v1
Requires HTTPS. All API requests must include your API key in the Authorization header.
Authorization: Bearer YOUR_API_KEY
Get your API key from the Console. Keep it secret. Never expose it in client-side code.
# Install: pip install openai from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://aicraftapi.com/v1" ) response = client.chat.completions.create( model="auto", # Auto Router picks the best model messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content)
// Install: npm install openai import OpenAI from "openai"; const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://aicraftapi.com/v1" }); const response = await client.chat.completions.create({ model: "auto", messages: [{ role: "user", content: "Hello!" }] }); console.log(response.choices[0].message.content);
curl https://aicraftapi.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{ "model": "auto", "messages": [{"role": "user", "content": "Hello!"}] }'
Set model: "auto" for automatic routing. Or specify a model ID directly:
| Use Case | Model ID | Why |
|---|---|---|
| Coding | deepseek-v4-flash | Global #1 · Fastest |
| Chinese content | qwen3.7-max | Native fluency |
| Translation | qwen3.5-turbo | Fast and affordable |
| Creative writing | kimi-k2.6 | Natural storytelling |
| Deep reasoning | deepseek-r1 | Chain-of-thought |
| Long context (1M) | gemini-3-pro | Massive context window |
| Premium coding | claude-sonnet-5 | Top accuracy (coming soon) |
Blended retail prices per 1M tokens. Subscriptions include CN models at lower rates via Auto Router. Full plan details on Pricing page.
| Model | Context | Price / 1M | Best For |
|---|---|---|---|
| DeepSeek V4 Flash | 1M | $0.20 | Fast · Q&A · Translation |
| DeepSeek V3.2 | 128K | $0.70 | Coding · Logic |
| DeepSeek R1 | 128K | $0.80 | Deep reasoning |
| DeepSeek V4 Pro | 1M | $0.80 | Advanced reasoning |
| Qwen3.5 Turbo | 32K | $0.25 | Fast · Simple tasks |
| Qwen3.5 Plus | 32K | $1.60 | Balanced · General |
| Qwen3.7 Max | 32K | $3.20 | Chinese content |
| Qwen-Coder | 32K | $3.20 | Code generation |
| GLM-5 Flash | 128K | $1.00 | Fast · Cost-efficient |
| GLM-5.2 | 128K | $1.80 | Complex reasoning |
| Kimi K2.6 | 128K | $1.10 | Creative writing |
| Kimi K2.7 Code | 128K | $1.60 | Coding · Code review |
| Doubao Lite | 32K | $0.40 | Efficient · Low cost |
| MiniMax M3 | 128K | $1.00 | Creative writing |
| Claude Haiku 4.5 | 200K | $2.20 | Fast · Summarization |
| Claude Opus 4.8 | 200K | $9.50 | Most complex tasks |
| Claude Sonnet 5 | 200K | TBD | Coming soon |
| GPT-4o | 128K | $6.00 | Multimodal · Vision |
| GPT-4o-mini | 128K | $1.60 | Fast · Cost-efficient |
| Gemini 3 Pro | 1M | $4.80 | Multimodal · Vision |
| Gemini 3.5 Flash | 1M | $3.30 | Fast · Summarization |
| Gemini 2.5 Pro | 1M | $1.70 | Balanced · Multimodal |
| Gemini Flash Lite | 1M | $0.12 | Lightweight · Edge |
| Grok 4.3 | 128K | $2.00 | Creative · Brainstorm |
| Mistral Large 3 | 128K | $1.90 | Multilingual · EU data |
| Llama 4 Maverick | 128K | $0.50 | Open source |
Blended retail prices. Detailed input/output rates in API response headers. International models billed at listed price + plan margin (20-25% for Pro, 15-20% for Max). Video models: Kling $0.50/video, Seedance $0.50/video (pass-through), Wan2.1 $0.35/video.
| Plan | Requests | Tokens / Month |
|---|---|---|
| Free | 5 / min | 5M (CN models) |
| Starter $19 | Unlimited | 40M (CN models) |
| Pro $49 | Unlimited | 110M (CN + Intl pay-per-use) |
| Max $99 | Unlimited | 220M (CN + Intl pay-per-use) |
| Team $199 | Unlimited | 400M · 5 seats · SLA 99.5% |
| Business $499 | Unlimited | 1B · 20 seats · SLA 99.9% |
| Enterprise | Unlimited | Custom · SLA 99.95% |
| Code | Meaning |
|---|---|
| 401 | Invalid or missing API key |
| 429 | Rate limit exceeded. Upgrade your plan. |
| 500 | Model temporarily unavailable. Auto Router will retry. |