Llama 4 Behemoth API Pricing
Open-weight · 1000K context · Available from 7 hosts. Cheapest: Novita at $0.72 input / $2.16 output per 1M tokens.
Llama 4 Behemoth price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.72 | $2.16 | $2.88 |
| DeepInfra | $0.765 | $2.295 | $3.06 |
| Groq | $0.855 | $2.565 | $3.42 |
| Meta | $0.9 | $2.7 | $3.6 |
| Together | $0.9 | $2.7 | $3.6 |
| OpenRouter | $0.9 | $2.7 | $3.6 |
| Fireworks | $0.945 | $2.835 | $3.78 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Llama 4 Behemoth cost calculator
Frequently asked
How much does Llama 4 Behemoth cost per 1M tokens?
Llama 4 Behemoth costs $0.72 per 1M input tokens and $2.16 per 1M output tokens at its cheapest host (Novita).
What is Llama 4 Behemoth's context window?
Llama 4 Behemoth supports a context window of about 1000K tokens. Remember every token in the context is billed on each call.
Where is Llama 4 Behemoth cheapest to run?
Across 7 hosts, Novita is currently cheapest at $0.72/$2.16 per 1M tokens, versus Fireworks at $0.945/$2.835. Prices change often — use the comparison table above.