model · class value · updated 2026-08-21
What it's for
Best for: Self-hosting, customization, and privacy-aware workloads.
Not ideal for: Managed convenience or top-tier reasoning out of the box.
Role: Open-weight / flexible deployment model
Specifications
| Provider | Meta |
| API format | openai |
| Context window | 1048576 |
| Restricted access | No |
| Capabilities | Vision, Tools |
| Execution Paths | api, self_host |
Price components
| Type | USD | Basis | Conditions | Source | Verified | Freshness |
|---|---|---|---|---|---|---|
| per_million_in | $0.20 | required · verified | OpenRouter default price-weighted routing observation; this pair matched the DeepInfra FP8 Llama 4 Maverick endpoint on 2026-07-29, but the actual routed provider and billed rate can vary with availability, quantization, and routing preferences. | OpenRouter Llama 4 Maverick routing price row | 2026-08-21 | vendor · 0d |
| per_million_out | $0.80 | required · verified | OpenRouter default price-weighted routing observation; this pair matched the DeepInfra FP8 Llama 4 Maverick endpoint on 2026-07-29, but the actual routed provider and billed rate can vary with availability, quantization, and routing preferences. | OpenRouter Llama 4 Maverick routing price row | 2026-08-21 | vendor · 0d |
Cost at three usage tiers
| A few questions and small tasks each day. | $1.92/mo |
| Daily use, plus some scheduled tasks. | $6.40/mo |
| Working for you most of the day, including web tasks. | $19.20/mo |
Token cost only; add a host for the full-stack estimate.
Compare