Provider
Vertex AI Llama Models
Use this page to inspect prices within one provider and, when reviewed route identity exists, compare the same model across other providers.
Listed models 11
Chat
Chat models 11
Rows with mode=chat
Lowest input $0.2500 / 1M tokens
Vs global median: 0.5x
Lowest output $0.7000 / 1M tokens
Vs global median: 0.4x
Model pricing
11 rows include direct source URLs. Real invoices can still vary by discounts, regions, and cache rules.
| Model | Mode | Input | Output | Context | Other routes | Lowest elsewhere |
|---|---|---|---|---|---|---|
| llama-3.1-405b-instruct-maas Source linked | Chat | $5.0000 / 1M tokens | $16.0000 / 1M tokens | 2.0K | N/A | N/A |
| llama-3.1-70b-instruct-maas Source linked | Chat | N/A | N/A | 2.0K | N/A | N/A |
| llama-3.1-8b-instruct-maas Source linked | Chat | N/A | N/A | 2.0K | N/A | N/A |
| llama-3.2-90b-vision-instruct-maas Source linked | Chat | N/A | N/A | 2.0K | N/A | N/A |
| llama-4-maverick-17b-128e-instruct-maas Source linked | Chat | $0.3500 / 1M tokens | $1.1500 / 1M tokens | 1.0M | N/A | N/A |
| llama-4-maverick-17b-16e-instruct-maas Source linked | Chat | $0.3500 / 1M tokens | $1.1500 / 1M tokens | 1.0M | N/A | N/A |
| llama-4-scout-17b-128e-instruct-maas Source linked | Chat | $0.2500 / 1M tokens | $0.7000 / 1M tokens | 10.0M | N/A | N/A |
| llama-4-scout-17b-16e-instruct-maas Source linked | Chat | $0.2500 / 1M tokens | $0.7000 / 1M tokens | 10.0M | N/A | N/A |
| llama3-405b-instruct-maas Source linked | Chat | N/A | N/A | 32.0K | N/A | N/A |
| llama3-70b-instruct-maas Source linked | Chat | N/A | N/A | 32.0K | N/A | N/A |
| llama3-8b-instruct-maas Source linked | Chat | N/A | N/A | 32.0K | N/A | N/A |