Providers /Google Vertex AI
Inference provider · HQ US

Google Vertex AI

Models
62
Regions
00

Our take

Editorial by LLMap · updated Aug 2, 2026

Google Vertex AI is a compliance-forward US cloud with the deepest catalogue of downloadable-model offers we track. It combines strong enterprise guardrails with mid-market pricing that is predictable rather than the absolute cheapest.

Use this for enterprise workloads needing verified SOC 2, EU data residency, and zero-retention guarantees. Pick it for broad model evaluation across 61 offers. Choose it when compliance documentation matters more than the lowest price. Skip it if price alone drives your choice, or if you need published benchmark scores.

Strengths
  • Deepest downloadable-model catalogue tracked — 61 offers.
  • Strongest compliance documentation in the sample set: SOC 2, EU endpoint, zero-retention, and no-training-on-prompts all verified.
  • Highest throughput sample for openai-gpt-oss-120b at 245 TPS.
  • Price-competitive on smaller parameter models, with openai-gpt-oss-120b several times cheaper than larger alternatives in the same catalogue.
Trade-offs
  • Premium pricing on larger or newer models, with steep output premiums and one showing output more than double input.
  • Throughput inconsistent for identical configurations, with one model showing a 2.5× spread across samples.
  • No benchmark scores disclosed for any of the 61 offers.
01

Privacy & data handling

Yes
No
No answer on record

The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.

Trains on your prompts
No
Logs prompts
No
Offered
Attested

Prompt retention: none.

02

Models & pricing

Claude Fable 5$11.00 / $55.00 /1M1M11m agoClaude Fable 5$10.00 / $50.00 /1M1M11m agoClaude Haiku 4.5$1.10 / $5.50 /1M200K11m agoClaude Haiku 4.5$1.00 / $5.00 /1M200K11m agoClaude Opus 4$15.00 / $75.00 /1M200K11m agoClaude Opus 4.1$15.00 / $75.00 /1M200K11m agoClaude Opus 4.5$5.00 / $25.00 /1M200K11m agoClaude Opus 4.6$5.00 / $25.00 /1M1M11m agoClaude Opus 4.6$5.50 / $27.50 /1M1M11m agoClaude Opus 4.7$5.00 / $25.00 /1M1M11m agoClaude Opus 4.7$5.50 / $27.50 /1M1M11m agoClaude Opus 4.8$5.00 / $25.00 /1M1M11m agoClaude Opus 4.8$5.50 / $27.50 /1M1M11m agoClaude Opus 5$5.00 / $25.00 /1M1M11m agoClaude Opus 5$5.50 / $27.50 /1M1M11m agoClaude Sonnet 4.5$3.30 / $16.50 /1M1M11m agoClaude Sonnet 4.5$3.00 / $15.00 /1M1M11m agoClaude Sonnet 4.6$3.00 / $15.00 /1M1M11m agoClaude Sonnet 4.6$3.00 / $15.00 /1M1M11m agoClaude Sonnet 4.6$3.00 / $15.00 /1M1M11m agoClaude Sonnet 4.6$3.30 / $16.50 /1M1M11m agoClaude Sonnet 5$2.00 / $10.00 /1M1M11m agoClaude Sonnet 5$2.20 / $11.00 /1M1M11m agoDeepSeek V3.1 Terminus685B$0.60 / $1.70 /1M164K11m agoDeepSeek V3.2685B$0.56 / $1.68 /1M164K11m agoGemini 2.5 Flash$0.30 / $2.50 /1M1M11m agoGemini 2.5 Flash$0.30 / $2.50 /1M1M38h agoGemini 2.5 Flash$0.30 / $2.50 /1M1M11m agoGemini 2.5 Flash Lite$0.10 / $0.40 /1M1M11m agoGemini 2.5 Flash Lite$0.10 / $0.40 /1M1M11m agoGemini 2.5 Pro$1.25 / $10.00 /1M1M11m agoGemini 2.5 Pro$1.25 / $10.00 /1M1M11m agoGemini 2.5 Pro$0.63 / $5.00 /1M1M11m agoGemini 2.5 Pro Preview 05-06$1.25 / $10.00 /1M1M11m agoGemini 2.5 Pro Preview 05-06$0.63 / $5.00 /1M1M11m agoGemini 2.5 Pro Preview 05-06$1.25 / $10.00 /1M1M11m agoGemini 2.5 Pro Preview 05-06$0.63 / $5.00 /1M1M32h agoGemini 3.1 Flash Lite$0.13 / $0.75 /1M1M6h agoGemini 3.1 Pro Preview Custom Tools$1.00 / $6.00 /1M1M11m agoGemini 3.5 Flash$0.75 / $4.50 /1M1M11m agoGemini 3.5 Flash Lite$0.15 / $1.25 /1M1M11m agoGemini 3.6 Flash$0.75 / $3.75 /1M1M11m agoGemini 3 Flash Preview$0.25 / $1.50 /1M1M11m agoGemma 4 26B A4B26.5B$0.15 / $0.60 /1M262K6h agoGLM 4.7358B$0.60 / $2.20 /1M200K6h agogpt-oss-120b120B$0.090 / $0.36 /1M131K9m agogpt-oss-safeguard-20b21.5B$0.070 / $0.25 /1M131K9m agoKimi K2 Thinking1.1T$0.60 / $2.50 /1M262K10m agoLlama 3.3 70B Instruct70.6B$0.72 / $0.72 /1M128K10m agoLlama 3.3 70B Instruct70.6B$0.72 / $0.72 /1M128K10m agoLlama 4 Maverick402B$0.35 / $1.15 /1M524K10m agoLlama 4 Scout109B$0.25 / $0.70 /1M1.3M10m agoMiniMax M2229B$0.30 / $1.20 /1M197K10m agoNano Banana 2 (Gemini 3.1 Flash Image)$0.50 / $3.00 /1M131K11m agoNano Banana 2 (Gemini 3.1 Flash Image Preview)$0.50 / $3.00 /1M131K8d agoNano Banana 2 Lite (Gemini 3.1 Flash Lite Image)$0.25 / $1.50 /1M66K11m agoNano Banana (Gemini 2.5 Flash Image)$0.15 / $1.25 /1M33K11m agoNano Banana Pro (Gemini 3 Pro Image)$2.00 / $12.00 /1M66K11m agoQwen3 235B A22B Instruct 2507235B$0.22 / $0.88 /1M262K9m agoQwen3 Coder 480B A35B480B$0.22 / $1.80 /1M262K9m agoQwen3 Next 80B A3B Instruct81.3B$0.15 / $1.20 /1M262K9m agoQwen3 Next 80B A3B Thinking81.3B$0.15 / $1.20 /1M262K9m ago
Something wrong on this page? Tell us