Llama 4 Maverick 17B Instruct pricing & specs

Meta · released 2025-04-05 · ● verified 2026-10-11

input / 1M$0.27via Novita AI
output / 1M$0.85via Novita AI
context1.05M
max output8.2K

// price history ($/1M tokens)

$0.9775
input $/1Moutput $/1M2025-04-05 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Llama 4 Maverick 17B Instruct
Qwen3.7 Flash$0.03$0.131M−86.7%
Qwen3.5 Flash$0.10$0.401M−57.8%
Gemini 2.5 Flash-Lite$0.10$0.401.05M−57.8%
Claude Haiku 5.5$0.10$0.501M−51.8%
GPT-6 Luna$0.10$0.501.05M−51.8%

// price by host

hostin $/1Mout $/1M
Novita AI$0.27$0.85
Amazon Bedrock$0.24$0.97

// faq

How much does Llama 4 Maverick 17B Instruct cost?

Llama 4 Maverick 17B Instruct costs $0.27 per million input tokens and $0.85 per million output tokens (cheapest tracked host: Novita AI). At 50M input and 10M output tokens per month that is about $22.00.

What is the context window of Llama 4 Maverick 17B Instruct?

1.05M tokens, with up to 8.2K output tokens per request.

What are cheaper alternatives to Llama 4 Maverick 17B Instruct?

Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen3.5 Flash ($0.10 in / $0.40 out), Gemini 2.5 Flash-Lite ($0.10 in / $0.40 out) offer the same input types and capabilities for less.

Is Llama 4 Maverick 17B Instruct open weights?

Yes. It is available from 2 tracked hosts; the cheapest is Novita AI at $0.27 input and $0.85 output per million tokens.

// spec sheet

input / 1M
$0.27
output / 1M
$0.85
blended (3:1)
$0.415
context
1.05M
max output
8.2K
input types
text · image
reasoning
no
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
2024-08
price source
Novita AI

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Qwen3.7 Flash$0.03$0.13$2.80
Gemini 2.5 Flash-Lite$0.10$0.40$9.00
Qwen3.5 Flash$0.10$0.40$9.00
Llama 4 Maverick 17B Instruct$0.27$0.85$22.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.