SambaNova Cloud Serverless AI Token Pricing & API Rates
Verified RatesCustom Dataflow Silicon DatacenterReal-time verified rates (Updated 2026)
SambaNova Cloud Serverless AI Token Pricing (4 Models)
| Model | Category | Cold Start | Context | Input ($/1M or Unit) | Output / 1M Tokens | Speed | Actions |
|---|---|---|---|---|---|---|---|
| Llama-3.1-8B-Instruct | LLM | 0s Instant | 128K | $0.10 | $0.20 | 850 tps | API Docs |
| Llama-3.3-70B-Instruct | LLM | 0s Instant | 128K | $0.60 | $1.20 | 420 tps | API Docs |
| Qwen2.5-72B-Instruct | LLM | 0s Instant | 128K | $0.70 | $1.40 | 380 tps | API Docs |
| Llama-3.1-405B-Instruct | REASONING | 0s Instant | 128K | $5.00 | $10.00 | 105 tps | API Docs |
Simulate monthly input and output token volume on SambaNova Cloud and compare your savings against OpenAI GPT-4o and Claude 3.5.
Open SambaNova Cloud Cost CalculatorCompare alternative inference platforms like Groq, Together AI, and DeepInfra on token latency, context windows, and pricing.
View Alternatives ComparisonSambaNova Cloud Pricing FAQ & Cost Guide
How does serverless token billing work on SambaNova Cloud?
SambaNova Cloud meters exact input (prompt) and output (completion) tokens. You only pay for what your application generates. There is zero baseline server provisioning cost or ongoing hourly commitment.
Does SambaNova Cloud charge for stopped instances or idle storage?
No. SambaNova Cloud is a purely serverless platform. When your application receives zero traffic, your hourly billing is strictly $0.00. There are no persistent disk fees or stopped instance retention charges.
Are there hidden egress or bandwidth fees?
Egress on SambaNova Cloud is billed at Free / Included in Token Rate.
What payment methods does SambaNova Cloud accept?
SambaNova Cloud accepts standard credit card billing and enterprise invoicing with verified business accounts.