Replicate vs Google Vertex AI

Same workloads, both price lists, refreshed daily. On shared line items today: Replicate is cheaper on 0 of 13 shared models (input or output price), Google Vertex AI on 7.

Replicate

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..

  • Massive community model zoo
  • Per-second billing, scale to zero
  • Custom models via Cog

Visit Replicate

Google Vertex AI

Gemini plus 100+ models in Google Cloud's ML platform, with enterprise governance, grounding and tuning pipelines..

  • Enterprise governance
  • Grounding with Google Search
  • Model Garden variety

Visit Google Vertex AI

Shared models, priced by both

List prices refreshed 2026-08-23 ยท input $/1M tokens
Model Replicate in/out Google Vertex AI in/out Cheaper input
GPT-OSS 20B $0.090 / $0.360 $0.075 / $0.300 Google Vertex AI
GPT-OSS 120B $0.180 / $0.720 $0.090 / $0.360 Google Vertex AI
Qwen3 235B A22B $0.264 / $1.06 $0.220 / $0.880 Google Vertex AI
DeepSeek-V3.1 $0.672 / $2.02 $0.600 / $1.70 Google Vertex AI
Claude Haiku 4.5 $1.00 / $5.00 $1.00 / $5.00 tie
Claude-3.5-Haiku $1.00 / $5.00 $1.00 / $5.00 tie
Gemini-3-Pro $2.00 / $12.00 $2.00 / $12.00 tie
Gemini 2.5 Flash $2.50 / $2.50 $0.300 / $2.50 Google Vertex AI
Claude-3.7-Sonnet $3.00 / $15.00 $3.00 / $15.00 tie
Claude Sonnet 4 $3.00 / $15.00 $3.00 / $15.00 tie
Claude Sonnet 4.5 $3.00 / $15.00 $3.00 / $15.00 tie
DeepSeek R1 $3.75 / $10.00 $1.35 / $5.40 Google Vertex AI
Claude-3.5-Sonnet $3.75 / $18.75 $3.00 / $15.00 Google Vertex AI

Cheaper-on-count is a tally of listed prices, not a quality verdict: throughput, reliability and quantization differ between providers. Disclosure.