DeepSeek returned a rate limit error:

Error: Rate limit exceeded. Please wait before retrying.

Here is how to fix it.

Fix 1: Check your tier

DeepSeek has different limits by tier:

# Check rate limit headers
curl -I https://api.deepseek.com/v1/chat/completions \
  -H "Authorization: Bearer $DEEPSEEK_API_KEY"

Limits by tier:

• Free: 10 requests/minute
• Pay-as-you-go: 60 requests/minute
• Enterprise: Custom

Fix 2: Implement retry with backoff

import time
import random

def call_with_retry(prompt, max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="deepseek-v4-pro",
                messages=[{"role": "user", "content": prompt}]
            )
        except openai.RateLimitError:
            wait = min(60, (2 ** attempt) + random.uniform(0, 1))
            print(f"Rate limited, waiting {wait:.1f}s...")
            time.sleep(wait)
    raise Exception("Max retries exceeded")

Fix 3: Use batch processing

Combine multiple requests:

# Instead of 10 separate requests
results = []
for item in items:
    response = call(item)
    results.append(response)

# Use batch API (50% cheaper, higher limits)
batch_items = [{"custom_id": str(i), "body": item} for i, item in enumerate(items)]

Fix 4: Switch to Flash model

DeepSeek V4 Flash has higher rate limits:

# Pro: Lower limits
model = "deepseek-v4-pro"

# Flash: Higher limits, faster
model = "deepseek-v4-flash"

Fix 5: Use multiple API keys

Rotate keys for higher throughput:

api_keys = ["key1", "key2", "key3"]
current = 0

def get_key():
    global current
    key = api_keys[current]
    current = (current + 1) % len(api_keys)
    return key

Fix 6: Cache responses

Reduce API calls with caching:

import hashlib
import json

cache = {}

def cached_request(prompt):
    key = hashlib.md5(prompt.encode()).hexdigest()
    if key in cache:
        return cache[key]
    
    response = call_api(prompt)
    cache[key] = response
    return response

Still not working?

1. Upgrade tier — More requests per minute
2. Use OpenRouter — Different rate limits
3. Wait for reset — Limits reset every minute
4. Contact support — Request limit increase

FAQ

What are DeepSeek’s rate limits?

Free tier: 10 requests/minute. Pay-as-you-go: 60 requests/minute. Enterprise: Custom. Limits vary by tier and model. Check your usage in the DeepSeek dashboard.

How do I increase my rate limit?

Upgrade to a paid tier for higher limits. You can also use multiple API keys, implement caching, or switch to a faster model like DeepSeek V4 Flash.

Does DeepSeek have daily limits?

Free tier has daily limits. Pay-as-you-go does not have daily limits, only per-minute limits. Enterprise plans have custom limits.

Related: DeepSeek V4 Complete Guide · DeepSeek API Timeout Fix · AI API Pricing Compared 2026 · OpenRouter Complete Guide