Yi-34B
Open Base
Open-weights Yi-34B base. Designed for downstream fine-tuning rather than direct chat use.
Yi-34B is a frontier AI model from 01.AI. It costs $0.800 per million input tokens and $0.800 per million output tokens (blended $0.800/M), with a 4,000-token context window.
INPUT
$0.800/M
per million input tokens
OUTPUT
$0.800/M
per million output tokens
CONTEXT
4,000
tokens
What it is good at
- Open-weights base
- Strong bilingual base
- 200K-context variants available
Typical use cases
- Fine-tune base
- Continued pretraining experiments
Benchmarks
vs. best public score
Scores inherited from Yi-34B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
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 →Yi-Lightning
Fast · 16,000 ctx
in $0.140/Mout $0.140/M
Yi-Large
Frontier · 32,000 ctx
in $3.000/Mout $3.000/M
Yi-Large-Turbo
Balanced · 16,000 ctx
in $0.380/Mout $0.380/M
Yi-34B-Chat
Open Large · 4,000 ctx
in $0.800/Mout $0.800/M
Yi-9B
Compact · 4,000 ctx
in $0.300/Mout $0.300/M
Yi-6B
Nano · 4,000 ctx
in $0.150/Mout $0.150/M
Frequently asked questions
How much does Yi-34B cost?
Yi-34B costs $0.800 per million input tokens and $0.800 per million output tokens, for a blended reference rate of $0.800 per million tokens.
What is Yi-34B's context window?
Yi-34B supports up to 4,000 tokens of context in a single request.
What is Yi-34B best for?
Yi-34B is well suited to Open-weights base, Strong bilingual base and 200K-context variants available.
Who makes Yi-34B?
Yi-34B is developed and served by 01.AI. It was released in Nov 2023.