- Input price
- $0.35 / 1M tokens
- Output price
- $1.00 / 1M tokens
- Context window
- 524K tokens
- Longest reply
- 33K tokens
About this model
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...
Description from the model’s public catalogue listing.
Capabilities
- Reads
- Text, Image
- Writes
- Text
- Reasoning mode
- No
- Tool calling
- Yes
- Open weights
- Yes
- Cached input
- $0.17 / 1M tokens
What it would cost
At list price, without caching or batch discounts.
- 1,000 chat replies2K tokens in, 500 out each
- $1.20
- Summarise 100 long reports50K tokens in, 1K out each
- $1.85
- A coding agent’s working day20M tokens in, 1M out
- $8.00
Price history
Per 1M tokens, input then output. Tracked since 30 Sept 2026.
- 5 Nov 2026
- $0.19 → $0.35+87%$0.65 → $1.00+53%
Alternatives at a similar price
From other labs, priced within about 40% of Llama 4 Maverick, with a comparable context window.
- Inkling 2 SmallThinking Machines, 1.05M context$0.30 in$1.00 out
- Hy4Tencent, 1.05M context$0.42 in$1.25 out
- Motif 3Motif Technologies, 262K context$0.30 in$1.20 out
- GLM 5.3 FlashX LegalZ.ai, 1.05M context$0.37 in$1.25 out
- Beam 1.0 501B A23BReflection, 1.05M context$0.30 in$1.00 out
- MiMo-V2.6-ProXiaomi, 1.05M context$0.43 in$0.87 out
More from Meta
See all- Muse EmberMeta, 1.05M context$0.10 in$0.50 out
- Muse Spark OpenMeta, 1.05M context$1.25 in$4.25 out
- Muse WonderMeta, 1.05M context$4.00 in$20 out
- Muse Spark 1.3 ContributorMeta, 1.05M context$0.10 in$0.20 out
- Muse Spark 1.3Meta, 1.05M context$1.25 in$4.25 out
- Muse Spark 1.2 ContributorMeta, 1.05M context$0.10 in$0.20 out