Llama 4 Maverick 17B 128E Instruct
Meta
Key facts · verified Oct 29, 2026
Llama 4 Maverick 17B 128E Instruct is a Meta model released on 5 Apr 2025. Its API price is $0.63 per million input tokens and $1.80 per million output tokens. Its context window is 1M tokens. It ranks #252 on LMArena's text leaderboard (Elo 1327, read 1 Nov 2026). Source: ai.meta.com.
Llama 4 Maverick 17B 128E Instruct is an open-weight model from Meta, released on April 5, 2025 under the Llama 4 licence, so it can be self-hosted. Meta's model card lists a 1M-token context window. Third-party hosts listed by LMArena price it at $0.63 per million input tokens and $1.80 per million output tokens, and on LMArena it holds 1327 Elo (rank 252).
Pricing & specs checkedSource: vendor documentation · checked Oct 29, 2026LMArena: 1327 Elo (rank 252) · source · retrieved Nov 1, 2026
Full Specifications
$0.63 / $1.80 per million tokens | |
|---|---|
| Identity | |
| Developer | Meta |
| Released | Apr 2025 |
| Licence | Llama 4 |
| Self-hostable | Yes |
| Cost | |
| Blended $/1M tokensinput × 0.75 + output × 0.25 | $0.923 / 1M tokens |
| Input price | $0.630 / 1M tokens |
| Output price | $1.800 / 1M tokens |
| Capacity | |
| Context window | 1M tokens |
| Measured quality | |
| LMArena Elo | 1327 (checked Nov 2026) |
| LMArena rank | Rank 252 |
| Elo per dollarLMArena Elo ÷ blended $/1M tokens | 1438 |