Aggregator
Replicate
/replicate · San Francisco, USA · est. 2019
Data: mediumVisit provider ↗
Key facts
- Replicate is a aggregator headquartered in San Francisco, USA, founded 2019.
- Uses its own native API dialect rather than an OpenAI-compatible endpoint.
- Blended reference price is $1.70 per 1M tokens (in $0.65 / out $2.75).
- Reference latency 900 ms TTFT at 60 tok/s throughput, with 99.3% reference uptime.
- Editorial reputation index 80/100 from 410 weighted signals; 90-day trend stable.
Specification
- Category
- Aggregator
- Headquarters
- San Francisco, USA
- Founded
- 2019
- Model access
- Open weights
- Flagship / served
- Community + language models
- Reference open model
- Llama 3.3 70B
- OpenAI-compatible API
- No (native API)
- Blended $/1M
- $1.70 seed
Strengths & trade-offs
Strength
Broadest catalog including image, audio and video models.
Trade-off
Cold starts and its own (non-OpenAI) API shape for LLMs.
Profile reviewed 2026-07-10. Confidence for this listing:medium — Figure based on public sources but not re-confirmed on the exact review date; may drift.Not affiliated with Replicate. ← Back to directory