Llama 4 Scout 17B 16E Instruct
azure-cognitive-services/llama-4-scout-17b-16e-instruct · family llama · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.35
Blended $/1M (3:1)
$0.2
Input $/1M
$0.78
Output $/1M
$0.98
1M in + 1M out
—
Cache read $/1M
#2339 of 7,708
Cheapest rank
- Provider
- Azure Cognitive Services (
azure-cognitive-services) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools text image
Same model, other providers
“Llama 4 Scout 17B 16E Instruct” is offered by 3 providers — cheapest-effective first. This one (Azure Cognitive Services) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Azure Cognitive Services (this) | $0.2 | $0.78 | $0.35 | 128k |
| Azure | $0.2 | $0.78 | $0.35 | 128k |
| Cloudflare Workers AI | $0.27 | $0.85 | $0.42 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Azure Cognitive Services and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"llama-4-scout-17b-16e-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):