DeepInfra Serverless AI Token Pricing & API Rates
Verified RatesTier 3 Serverless CloudReal-time verified rates (Updated 2026)
DeepInfra Serverless AI Token Pricing (7 Models)
| Model | Category | Cold Start | Context | Input ($/1M or Unit) | Output / 1M Tokens | Speed | Actions |
|---|---|---|---|---|---|---|---|
| FLUX.1-dev | IMAGE | 0s Instant | 1K | $0.025 / img | — | Stateless API | API Docs |
| Meta-Llama-3.1-8B-Instruct | LLM | 0s Instant | 128K | $0.05 | $0.08 | 160 tps | API Docs |
| Qwen-2.5-Coder-32B-Instruct | LLM | 0s Instant | 128K | $0.12 | $0.16 | 95 tps | API Docs |
| DeepSeek-V3 | LLM | 0s Instant | 64K | $0.14 | $0.28 | 75 tps | API Docs |
| Llama-3.3-70B-Instruct | LLM | 0s Instant | 128K | $0.23 | $0.40 | 85 tps | API Docs |
| Qwen-2.5-72B-Instruct | LLM | 0s Instant | 128K | $0.35 | $0.40 | 80 tps | API Docs |
| DeepSeek-R1 | LLM | 0s Instant | 160K | $0.55 | $2.19 | 65 tps | API Docs |
Simulate monthly input and output token volume on DeepInfra and compare your savings against OpenAI GPT-4o and Claude 3.5.
Open DeepInfra Cost CalculatorCompare alternative inference platforms like Groq, Together AI, and DeepInfra on token latency, context windows, and pricing.
View Alternatives ComparisonDeepInfra Pricing FAQ & Cost Guide
How does serverless token billing work on DeepInfra?
DeepInfra 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 DeepInfra charge for stopped instances or idle storage?
No. DeepInfra 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 DeepInfra is billed at Included in Token Pricing.
What payment methods does DeepInfra accept?
DeepInfra accepts standard credit card billing and enterprise invoicing with verified business accounts.