DeepSeek-V3.2 (Preview) by SambaNova
Free tier, no credit card. Ultra-fast RDU inference. 20 RPM, 200K tokens/day.
Access
Free API tier
Free limits
20 RPM, 20 RPD, 200K TPD
Modality
text
Credit card
Not required
Commercial use
Unclear, verify
Context window
128,000 tokens
Rate limit
20 RPM · 20 RPD · 200,000 TPD
Model ID
DeepSeek-V3.2
Base URL
https://api.sambanova.ai/v1
Last verified
June 2026
Quickstart
curl https://api.sambanova.ai/v1/chat/completions \
-H "Authorization: Bearer $KEY" \
-d '{"model":"DeepSeek-V3.2","messages":[{"role":"user","content":"hi"}]}'Frequently asked
Is DeepSeek-V3.2 (Preview) free?
Yes. SambaNova offers it as Free API tier with these limits: 20 RPM, 20 RPD, 200K TPD. No credit card is required.
Can I use DeepSeek-V3.2 (Preview) commercially?
Commercial terms are not clearly documented. Check the provider's current terms before shipping.
How do I start using DeepSeek-V3.2 (Preview)?
Free tier, no credit card. Ultra-fast RDU inference. 20 RPM, 200K tokens/day.
Building with this model?
We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps.
Free monthly update
The monthly free-models update
What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.
Related free models
- Kimi K2.6 (Ollama Cloud) · Free tier
- GLM 4.6 (Z.ai) · Self-host free
- Gemini 3.5 Flash (Google Gemini) · 15 RPM, 1,500 RPD
- Gemini 2.5 Flash (Google AI Studio) · Generous · no card
- DeepSeek V3-0324 (DeepSeek) · Self-host free
- Gemini 2.5 Pro (Google Gemini) · 5 RPM, 50 RPD