Llama-4-Maverick-17B-128E-Instruct
SambaNovaPricing, specs, and comparison for Llama-4-Maverick-17B-128E-Instruct by SambaNova.
Input Cost
$0.630
/1M tokens
Output Cost
$1.80
/1M tokens
Context Window
131.1K
tokens
Max Output
131.1K
tokens
Features
VisionFunction Calling
Cost Examples
| Usage | Input Cost | Output Cost | Total |
|---|---|---|---|
| 1K tokens in + 500 out | $0.0006 | $0.0009 | $0.0015 |
| 10K tokens in + 2K out | $0.0063 | $0.0036 | $0.0099 |
| 100K tokens in + 10K out | $0.0630 | $0.0180 | $0.0810 |
| 1M tokens in + 100K out | $0.6300 | $0.1800 | $0.8100 |
Similar Models
Models in a similar price range from other providers.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| Llama-4-Maverick-17B-128E-Instruct | SambaNova | $0.630 | $1.80 | 131.1K |
| Mixtral-8x7B-Instruct-v0.1 | OVHcloud | $0.630 | $0.630 | 32K |
| deepseek.v3.2 | AWS Bedrock | $0.620 | $1.85 | 163.8K |
| us-east-1/deepseek.v3.2 | AWS Bedrock | $0.620 | $1.85 | 163.8K |
| us-east-2/deepseek.v3.2 | AWS Bedrock | $0.620 | $1.85 | 163.8K |
| us-west-2/deepseek.v3.2 | AWS Bedrock | $0.620 | $1.85 | 163.8K |
每周大模型价格速递
AI Model 调价时第一时间通知你。免费、不发垃圾邮件、随时退订。