Integrate once, access 19+ AI models. OpenAI-compatible API with built-in budget control.
Navigate to API Keys section, create a new key, and set your budget limits.
Point your OpenAI SDK to https://crawfish.top/v1
All API requests require authentication using Bearer tokens in the Authorization header:
# Header format
Authorization: Bearer sk-xxxxxxxxxxxxxxxx
Use this base URL for all API endpoints:
https://crawfish.top/v1
# Install: pip install openai
from openai import OpenAI
client = OpenAI(
api_key="sk-your-key-here",
base_url="https://crawfish.top/v1"
)
response = client.chat.completions.create(
model="deepseek-v4",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)
// Install: npm install openai
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: "sk-your-key-here",
baseURL: "https://crawfish.top/v1"
});
const response = await client.chat.completions.create({
model: "deepseek-v4",
messages: [
{role: "user", content: "Hello!"}
]
});
console.log(response.choices[0].message.content);
curl https://crawfish.top/v1/chat/completions \
-H "Authorization: Bearer sk-your-key-here" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'
Use any of these model IDs in the model parameter:
deepseek-v4 - Latest reasoning modeldeepseek-reasoner - Deep reasoningglm-4-flash - Fast responseglm-4-air - Balancedqwen-plus - Plus tierqwen-turbo - Fast & cheapqwen-long - Long contextdoubao-pro-32k - Pro 32Kdoubao-lite-32k - Lite 32Kmoonshot-v1-8k - 8K contextmoonshot-v1-32k - 32K contexternie-4.0-8k - Latest flagshipernie-3.5-8k - Stableernie-speed-8k - Fastsf-qwen2.5-72b - Qwen 72Bsf-deepseek-v3 - DeepSeek V3sf-glm-4-9b - GLM 9Bsf-llama4-scout - Llama 4 Scoutauto - Auto-select best model| Code | Meaning | Solution |
|---|---|---|
401 |
Authentication failed | Check your API key is correct |
429 |
Rate limit exceeded | Wait and retry, or contact support |
500 |
Internal server error | Check status page |
503 |
Service unavailable | Model may be temporarily down |
400 |
Invalid request | Check request format and parameters |
Crawfish API currently has no special rate limits. Rate limits are inherited from upstream providers.
Note: Limits may vary by model and your account tier. Check your dashboard for specific limits.
Need help? Contact us at support@crawfish.top
We typically respond within 24 hours on business days.