Aggregator
DeepInfra
/deepinfra · Palo Alto, USA · est. 2022
Data: highVisit provider ↗
Key facts
- DeepInfra is a aggregator headquartered in Palo Alto, USA, founded 2022.
- Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
- Blended reference price is $0.38 per 1M tokens (in $0.35 / out $0.40).
- Reference latency 360 ms TTFT at 110 tok/s throughput, with 99.5% reference uptime.
- Editorial reputation index 81/100 from 305 weighted signals; 90-day trend stable.
Specification
- Category
- Aggregator
- Headquarters
- Palo Alto, USA
- Founded
- 2022
- Model access
- Open weights
- Flagship / served
- Pay-per-token open models
- Reference open model
- Llama 3.3 70B
- OpenAI-compatible API
- Yes
- Blended $/1M
- $0.38 medium
Strengths & trade-offs
Strength
Aggressive per-token pricing on popular open models.
Trade-off
Fewer enterprise features than larger platforms.
Profile reviewed 2026-07-10. Confidence for this listing:high — Figure confirmed against the provider's public pricing/docs page on the last_reviewed date.Not affiliated with DeepInfra. ← Back to directory