deepseek
chat
Test your DeepSeek API key.
Validate a DeepSeek API key, list DeepSeek-Chat / Coder / Reasoner models, and benchmark latency.
Stateless proxy — keys never logged, stored, or persisted. What happens to your key →
Detected
DeepSeek
What this key does
DeepSeek's API is OpenAI-compatible. The current model list includes deepseek-chat (general) and deepseek-reasoner (chain-of-thought). Pricing is aggressively cheap for the capability tier.
How to get a DeepSeek API key
- Sign in at platform.deepseek.com.
- Top up the account (DeepSeek requires a positive balance to issue keys).
- Create an API key and paste it here.
Common errors and fixes
- 401 Unauthorized: Key is invalid, revoked, or pasted with extra whitespace. Generate a new key from the provider console and try again.
- 403 Forbidden: Key is valid but lacks permission for this resource. Check project / org / workspace scope, or that billing is set up for this key.
- 429 Too Many Requests: You hit the per-minute or per-day rate limit. Wait a moment and retry, or upgrade your tier.
- 404 Not Found: The endpoint or model id changed. Check the provider docs for the current path and model identifier.
- 5xx: The provider is having issues. Check their status page before assuming the bug is yours.
Security best practices
- Store keys in an env var or secret manager — never commit them to a repo, even a private one.
- Restrict scope: prefer per-project or per-deployment keys over a single root key shared across services.
- Rotate on a schedule (90 days is a sane default) and immediately on suspected leak.
- Audit usage in the provider console after rotation to confirm the old key has zero traffic.
- Set per-key spend limits where the provider supports them, so a leaked key has a bounded blast radius.
Pricing at a glance
DeepSeek is among the cheapest providers in the reasoning-class lane. Off-peak pricing offers an additional discount for batch-style workloads.
FAQ
- Is DeepSeek OpenAI-compatible?
- Yes — base URL https://api.deepseek.com/v1.
- What's the difference between deepseek-chat and deepseek-reasoner?
- Reasoner exposes chain-of-thought tokens and is priced higher. Chat is the general-purpose model.
- Where is DeepSeek hosted?
- China-based infrastructure. Latency from outside Asia is noticeably higher.
- Is there a free tier?
- Not in the standard sense — accounts need a positive balance to issue keys, but minimum top-up is small.
- Can I use OpenAI's Python SDK with DeepSeek?
- Yes, just swap base_url and api_key.
- Are there content policy differences?
- Yes, DeepSeek has its own content moderation. Some prompts that pass on US providers may be filtered.
Test other providers
Related reading
- OpenAI vs Anthropic pricing in 2026A side-by-side breakdown of OpenAI and Anthropic per-token pricing, batch discounts, and prompt-caching savings.
- Free LLM API keys for testing in 2026Which providers offer free credits, how long they last, and how to stretch them for prototyping without a credit card.