01.AI
Efficient

Yi-6B

Nano

Smallest Yi, 6B. Cheap edge-friendly bilingual base.

Yi-6B is a efficient AI model from 01.AI. It costs $0.1500 per million input tokens and $0.1500 per million output tokens (blended $0.1500/M), with a 4,000-token context window.

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

INPUT
$0.1500/M
per million input tokens
OUTPUT
$0.1500/M
per million output tokens
BLENDED 70/30
$0.1500/M
unchanged since 3 May
CONTEXT
4,000
tokens

Hand-maintained from 01.AI's published pricing; no check date on record.

What it is good at
  • Edge-friendly
  • Open weights
  • Bilingual
Typical use cases
  • On-device bilingual assistants
  • Fine-tune base

Benchmarks

vs. best public score
MMLU63.2%
Multitask academic knowledge across 57 subjects. Source: 01.AI (self-reported), MMLU, read 2026-11-10.
MATH4.6%
High-school competition math problems. Source: 01.AI (self-reported), MATH (4-shot, pass@1), read 2026-11-10.
HumanEval15.9%
Python function synthesis from docstrings. Source: 01.AI (self-reported), HumanEval, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from 01.AI

See all 9 →

Frequently asked questions

How much does Yi-6B cost?

Yi-6B costs $0.1500 per million input tokens and $0.1500 per million output tokens, for a blended reference rate of $0.1500 per million tokens.

What is Yi-6B's context window?

Yi-6B supports up to 4,000 tokens of context in a single request.

What is Yi-6B best for?

Yi-6B is well suited to Edge-friendly, Open weights and Bilingual.

Who makes Yi-6B?

Yi-6B is developed and served by 01.AI. It was released in Nov 2023.

Terms used on this page