Replicate pricing & review
Run thousands of community models (LLMs, image, audio, video) behind one API with per-second GPU billing: the fastest path from 'found a model on GitHub' to production endpoint.
Where Replicate wins
- Massive community model zoo
- Per-second billing, scale to zero
- Custom models via Cog
Replicate model pricing
List prices refreshed 2026-11-22 ยท cheapest 25 shown| Model | Input $/1M | Output $/1M | Market floor in |
|---|---|---|---|
| GPT-5 Nano | $0.050 | $0.400 | $0.050at Azure AI Foundry |
| Llama-3-8b | $0.050 | $0.250 | $0.030at DeepInfra |
| Granite 4.2 8B | $0.060 | $0.250 | $0.060at W&B Inference |
| GPT-OSS 20B | $0.090 | $0.360 | $0.015at Darkbloom |
| GPT-4.1 Nano | $0.100 | $0.400 | $0.100at Azure AI Foundry |
| GPT-4o-Mini | $0.150 | $0.600 | $0.150at Azure AI Foundry |
| Llama 4 Scout | $0.170 | $0.650 | $0.100at Vercel AI Gateway |
| GPT-OSS 120B | $0.180 | $0.720 | $0.030at W&B Inference |
| Llama Guard 4 12B | $0.200 | $0.200 | $0.180at DeepInfra |
| GPT-5 Mini | $0.250 | $2.00 | $0.250at Azure AI Foundry |
| Llama 4 Maverick | $0.250 | $0.950 | $0.200at Vercel AI Gateway |
| Qwen3 235B A22B | $0.264 | $1.06 | $0.140at OpenRouter |
| Qwen3.7 Plus | $0.276 | $1.10 | $0.276at Replicate |
| Gemini 2.5 Flash | $0.300 | $2.50 | $0.150at Oracle OCI |
| Mixtral-8x7B-Instruct-V0.1 | $0.300 | $1.00 | $0.150at Anyscale |
| GPT-4.1 Mini | $0.400 | $1.60 | $0.400at Azure AI Foundry |
| Gemini 3 Flash Preview | $0.500 | $3.00 | $0.500at Google Vertex AI |
| Llama-3-70b | $0.650 | $2.75 | $0.120at Hyperbolic |
| Kimi K2 Thinking | $0.660 | $2.70 | $0.600at AWS Bedrock |
| DeepSeek-V3.1 | $0.672 | $2.02 | $0.250at DeepInfra |
| Kimi K2.5 | $0.720 | $3.60 | $0.450at DeepInfra |
| Kimi K2.6 | $0.950 | $4.00 | $0.380at Clf AI Gateway |
| Claude Haiku 4.5 | $1.00 | $5.00 | $1.00at AWS Bedrock |
| GPT-5.6 Luna | $1.00 | $6.00 | $0.200at Azure AI Foundry |
| Claude-3.5-Haiku | $1.00 | $5.00 | $0.800at AWS Bedrock |