Llama 4 Maverick
- Input / output
- $0.35 / $1.00
- Providers
- 1
- Spread
- —
- 7 days
- 0%
- 30 days
- +68.7%
- Context
- 512K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
ParasailCheapest fp8 | $0.35 | $1.00 | $0.513 | ref |
- ParasailCheapest$0.513$0.35 in · $1.00 outref vs ref512K ctx100% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.513 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Parasail | $0.17 |
Changes
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- PriceCache read price,—→$0.05—
About
The cheapest provider for Llama 4 Maverick is Parasail at $0.513 per 1M tokens (blended), charging $0.35 per 1M input and $1.00 per 1M output tokens. It is served by a single provider. Its best price rose 68.7% over the last 30 days. Context window: 512K tokens. Prices tracked since Oct 3, 2026.
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...
- Released
- Apr 5, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- meta-llama/llama-4-maverick-17b-128e-instruct
- Weights
- meta-llama/Llama-4-Maverick-17B-128E-Instruct