Llama 4 Maverick API Pricing
Open-weight · 1000K context · Available from 7 hosts. Cheapest: Novita at $0.28 input / $0.92 output per 1M tokens.
Among Meta's 10 open-weight models tracked here, Llama 4 Maverick ($0.35/$1.15 per 1M tokens) is above Llama 3.3 70B ($0.71/$0.71) and below Llama 3.1 405B ($0.9/$0.9). Its 1000K context window is well above the open-weight category's typical range.
Llama 4 Maverick price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.28 | $0.92 | $1.2 |
| DeepInfra | $0.2975 | $0.9775 | $1.275 |
| Groq | $0.3325 | $1.0925 | $1.425 |
| Meta | $0.35 | $1.15 | $1.5 |
| Together | $0.35 | $1.15 | $1.5 |
| OpenRouter | $0.35 | $1.15 | $1.5 |
| Fireworks | $0.3675 | $1.2075 | $1.575 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Llama 4 Maverick cost calculator
Frequently asked
Llama 4 Maverick costs $0.28 per 1M input tokens and $0.92 per 1M output tokens at its cheapest host (Novita).
Llama 4 Maverick supports a context window of about 1000K tokens. Remember every token in the context is billed on each call.
Across 7 hosts, Novita is currently cheapest at $0.28/$0.92 per 1M tokens, versus Fireworks at $0.3675/$1.2075. Prices change often — use the comparison table above.