All AI models · LLM benchmarks · Methodology

Meta

Llama 4 Maverick 17B Instruct

Open multimodal Llama for strong reasoning with efficient everyday serving

Model facts

Context window
1.05M tokens
Maximum output
8K tokens
Cheapest paid input
$0.14 per 1M tokens
Cheapest paid output
$0.59 per 1M tokens
Open weights
yes
Providers
9

Capabilities and modalities

tool calling, structured output, attachments, temperature control, open weights, text, image.

Observed price history

  • 2026-08-24: $0.14 input / $0.59 output per 1M tokens

API providers

  • Abacus — model id meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8; $0.14 input / $0.59 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id llama-4-maverick-17b-instruct; $0.27 input / $0.85 output per 1M tokens; provider documentation
  • LLM Gateway (NovitaAI) — model id novita/llama-4-maverick-17b-instruct; $0.27 input / $0.85 output per 1M tokens; provider documentation
  • Charm Hyper — model id llama-4-maverick-17b-128e-instruct-fp8; $0.274 input / $0.899 output per 1M tokens; provider documentation
  • Amazon Bedrock — model id meta.llama4-maverick-17b-instruct-v1:0; $0.24 input / $0.97 output per 1M tokens; provider documentation
  • Amazon Bedrock (US) — model id us.meta.llama4-maverick-17b-instruct-v1:0; $0.24 input / $0.97 output per 1M tokens; provider documentation
  • LLM Gateway (AWS Bedrock) — model id aws-bedrock/llama-4-maverick-17b-instruct; $0.24 input / $0.97 output per 1M tokens; provider documentation
  • Neon — model id llama-4-maverick; $0.5 input / $1.5 output per 1M tokens; provider documentation
  • LLM Gateway (SCX.ai (Turbo)) — model id scx-ai/llama-4-maverick-17b-instruct; $0.53 input / $1.62 output per 1M tokens; provider documentation