meta/llama-4-maverick-17b-instructOpen multimodal Llama for strong reasoning with efficient everyday serving
meta/llama-4-maverick-17b-instruct| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 Cortecs | llama-4-maverick | 1M | $0.124 | $0.603 | $0.030 | · T · | View{
"cache_read": 0.03,
"cache_write": 0.151,
"input": 0.124,
"output": 0.603
} |
 Abacus | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1.04858M | $0.140 | $0.590 | — | · T · | View{
"input": 0.14,
"output": 0.59
} |
 Amazon Bedrock | meta.llama4-maverick-17b-instruct-v1:0 | 1M | $0.240 | $0.970 | — | · T · | View{
"input": 0.24,
"output": 0.97
} |
 LLM Gateway | llama-4-maverick-17b-instruct | 1.04858M | $0.270 | $0.850 | — | · · · | View{
"input": 0.27,
"output": 0.85
} |
 Neon | llama-4-maverick | 1M | $0.500 | $1.500 | — | · T · | View{
"input": 0.5,
"output": 1.5
} |