Fireworks AI
Fireworks AI
Frontier

Yi-34B (fw)

Open

Open-weights Yi-34B fine-tuned for chat. The model that put 01.AI on the open-weights map in 2023.

Yi-34B (fw) is a frontier AI model from Fireworks AI. It costs $0.900 per million input tokens and $0.900 per million output tokens (blended $0.900/M), with a 4,000-token context window.

Profile inherited from upstream Yi-34B ↗ — this is a hosted variant of the same open-weights model.

INPUT
$0.900/M
per million input tokens
OUTPUT
$0.900/M
per million output tokens
BLENDED 70/30
$0.900/M
unchanged since 3 May
CONTEXT
4,000
tokens
What it is good at
  • Open weights
  • Bilingual EN/ZH
  • 32K context
Typical use cases
  • Self-hosted bilingual chat
  • Fine-tune base

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.
MMLU73%
Multitask academic knowledge across 57 subjects.
Python function synthesis from docstrings.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Fireworks AI

See all 7 →

Frequently asked questions

How much does Yi-34B (fw) cost?

Yi-34B (fw) costs $0.900 per million input tokens and $0.900 per million output tokens, for a blended reference rate of $0.900 per million tokens.

What is Yi-34B (fw)'s context window?

Yi-34B (fw) supports up to 4,000 tokens of context in a single request.

What is Yi-34B (fw) best for?

Yi-34B (fw) is well suited to Open weights, Bilingual EN/ZH and 32K context.

Who makes Yi-34B (fw)?

Yi-34B (fw) is developed and served by Fireworks AI. It was released in Nov 2023.

Terms used on this page