Qwen
Frontier

Qwen2-57B-A14B

MoE

Qwen2 MoE, 57B total / 14B active. Cheap-to-serve MoE before Qwen2.5 closed the gap.

Qwen2-57B-A14B is a frontier AI model from Qwen. It costs $0.6500 per million input tokens and $0.6500 per million output tokens (blended $0.6500/M), with a 64,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.6500/M
per million input tokens
OUTPUT
$0.6500/M
per million output tokens
BLENDED 70/30
$0.6500/M
unchanged since 3 May
CONTEXT
64,000
tokens

Hand-maintained from Qwen's published pricing; no check date on record.

What it is good at
  • MoE efficiency
  • Open weights
  • Multilingual
Typical use cases
  • Cost-sensitive self-hosted chat
  • MoE research

Benchmarks

vs. best public score
MMLU75%
Multitask academic knowledge across 57 subjects. No source recorded yet.
Graduate-level science questions, "Google-proof". No source recorded yet.
MATH49%
High-school competition math problems. No source recorded yet.
Python function synthesis from docstrings. No source recorded yet.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Qwen

See all 22 →

Frequently asked questions

How much does Qwen2-57B-A14B cost?

Qwen2-57B-A14B costs $0.6500 per million input tokens and $0.6500 per million output tokens, for a blended reference rate of $0.6500 per million tokens.

What is Qwen2-57B-A14B's context window?

Qwen2-57B-A14B supports up to 64,000 tokens of context in a single request.

What is Qwen2-57B-A14B best for?

Qwen2-57B-A14B is well suited to MoE efficiency, Open weights and Multilingual.

Who makes Qwen2-57B-A14B?

Qwen2-57B-A14B is developed and served by Qwen. It was released in Jun 2024.

Terms used on this page