Llama 4 Scout 17B Instruct
google-vertex/meta/llama-4-scout-17b-16e-instruct-maas · family llama · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.36
Blended $/1M (3:1)
$0.25
Input $/1M
$0.7
Output $/1M
$0.95
1M in + 1M out
—
Cache read $/1M
#2500 of 7,973
Cheapest rank
- Provider
- Vertex (
google-vertex) - Kind
- text (outputs text)
- Context
- 1,310,720 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools text image
Same model, other providers
“Llama 4 Scout 17B Instruct” is offered by 4 providers — cheapest-effective first. DevPass (LLM Gateway) is the cheapest at $0.28 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| DevPass (LLM Gateway) | $0.18 | $0.59 | $0.28 | 131k |
| Amazon Bedrock | $0.17 | $0.66 | $0.29 | 10M |
| Vertex (this) | $0.25 | $0.7 | $0.36 | 1.3M |
| OCI Generative AI | $0.72 | $0.72 | $0.72 | 192k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vertex and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"meta/llama-4-scout-17b-16e-instruct-maas","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):