Llama 4 Scout 17B 16E Instruct
Wandb textwandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
Input
$0.1700
per 1M input tokens
Output
$0.6600
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
64,000
Max output
64,000
Effective date
Sep 6, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Sep 6, 2026 | $0.17 | $0.66 | $0.29 |
| Jun 15, 2026 | $17,000.00 | $66,000.00 | $29,250.00 |
Llama 4 Scout 17B 16E Instruct on other providers
Lambda Ai
· $0.0500 in / $0.1000 out
Gmi
· $0.0800 in / $0.5000 out
Nscale
· $0.0900 in / $0.2900 out
Deepinfra
· $0.1000 in / $0.3000 out
Groq
· $0.1100 in / $0.3400 out
Together Ai
· $0.1800 in / $0.5900 out
Novita
· $0.1800 in / $0.5900 out
Azure OpenAI
· $0.2000 in / $0.7800 out
Cloudflare
· $0.2700 in / $0.8500 out
Sambanova
· $0.4000 in / $0.7000 out
Other Wandb models
wandb/openai/gpt-oss-120b
· $0.1700/Mtok out
wandb/openai/gpt-oss-20b
· $0.1300/Mtok out
wandb/ibm-granite/granite-4.1-8b
· $0.1000/Mtok out
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
· $0.1000/Mtok out
wandb/OpenPipe/Qwen3-14B-Instruct
· $0.2200/Mtok out
wandb/ibm-granite/granite-4.2-8b
· $0.1500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.