Meta (via providers)Verified Active: September 18, 2026
Llama 4 MaverickAPI Pricing & Specifications
Leading open-weights frontier model for private, self-hosted or cloud inference.
📊 Core Specifications & Pricing Rates
Standard Input
$0.20 / 1M tokens
Standard Output
$0.60 / 1M tokens
Cached Input
None / 1M tokens
Context Window
1M (1,000,000 tokens)
Max Output Tokens
8,192 tokens
Supported Capabilities:✓ Vision✓ Function Calling / Tools✓ JSON Mode✓ Deep Reasoning
Live Workload Cost Estimator: Llama 4 Maverick
Adjust token volumes to simulate your exact monthly API bill.
Estimated Total Monthly Cost
Compare All Models in Calculator→$13.50/ month
$0.00054 per API request
💡 Estimated Monthly Workload Scenarios
Private On-Premise Enterprise Extraction
$34.00/mo50,000 hosted API queries (2,500 input, 300 output)
50,000 requests • 2500 in / 300 out
⚖️ Head-to-Head Competitor Comparisons
Llama 4 Maverick vs. DeepSeek V4-Flash
Llama 4 Maverick offers permissive open weights for self-hosting; hosted APIs are competitively priced at $0.20/$0.60.
Similar open-weights inference tierView DeepSeek V4-Flash →
📜 Historical Price Changes & Updates
2026-08-01
Llama 4 Maverick open weights distributed across cloud providers with 1M context.
🔗 Verified Primary Sources
All pricing, token limits, and capabilities are cross-checked against official provider documentation and live API endpoints.