Home / All model prices / Meta Llama / llama-4-maverick M Meta Llama
llama-4-maverick OpenRouter price Model overview Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Context window 1,048,576 tokens
Knowledge cutoff —
Price last verified 2026-09-06
First observed 2026-08-11 Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.
Current price Estimated API value in USD per million tokens, backed by OpenRouter's public Models API.
Input $0.2
Cached input —
Cache write 5m —
Cache write 1h —
Output $0.696 Capabilities and formats text image frequency penalty logit bias logprobs max tokens min p presence penalty repetition penalty response format seed stop structured outputs temperature tool choice tools top k top logprobs top p Performance references No comparable benchmark data is currently available.
PRICE EVOLUTION Price history Original observation and every later change, including any change of price source.
Original observed price Official price unavailable 2026-08-11
Input: — Cached input: — Cache write 5m: — Cache write 1h: — Output: —
Price change OpenRouter price 2026-08-20
Input: $0.2 Cached input: — Cache write 5m: — Cache write 1h: — Output: $0.8
Price change OpenRouter price 2026-08-31
Input: $0.2 Cached input: — Cache write 5m: — Cache write 1h: — Output: $0.696
