Meta: Llama 4 Maverick
micrometa-llama/llama-4-maverick
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...
AA INDEX9.3
CONTEXT524K
MODALITYtext+image->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED19 min ago
Input
$0.35 /M
Output
$1.00 /M
Blended (40/60)
$0.74 /M
Cost / IQ
$3.1831 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d↑ 9.0%
Price History
30-day view, daily close
Low: $0.62/M
High: $0.74/M
Average: $0.66/M
Pricing Variants
Cached Input
$0.05/M
73.3% cheaper than standard
Provider Comparison
3 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓DigitalOcean | $0.19 | $0.65 | $0.47 | -37.0% |
| Parasail | $0.35 | $1.00 | $0.74 | median |
| $0.35 | $1.15 | $0.83 | +12.2% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$3.1831/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #488 of 521 micro models
← YOU ARE HERE | Meta: Llama 4 Maverick
Data Sources
Source
Aggregator & direct provider data
3 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/meta-llama/llama-4-maverick
# Response (truncated)
{ "model_id": "meta-llama/llama-4-maverick", "name": "Meta: Llama 4 Maverick", "blended_price_per_m": 0.74, "sit_adjusted_price": 3.183129 }