AI Rankings
Yi-34B: Score, Price and Context Window
Data updated
- 01.AI
- Open weights
- Released Nov 2023
Its score range overlaps with Ministral 3B, the model just above it, so a small gap in rank is not a meaningful difference.
Best for
- Running it yourself: its weights can be downloaded (read the licence terms first).
Skip if
- Cutting-edge tasks: its overall Epoch score is in the lower part of the models we track.
- Long documents: its context window is only 4K tokens.
These lines are worked out from the numbers on this page, not from hands-on testing.
Key facts
- Price per million tokens
- $0.90 in / $0.90 out
- Blended $0.90. List price from Fireworks_ai, checked 26 Oct 2026.
We do not have an Arena human-vote rating for Yi-34B yet. It is shown as "Not measured" rather than guessed.
How Yi-34B stacks up
- Overall capability117.3
Better than 23% of the other 269 models
Epoch Capabilities Index: one score that combines many tests.
- Price$0.90 per 1M
Cheaper than 55% of the other 200 priced modelsUpper half
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
- Context window4K tokens
Larger context window than 0% of the other 198 models
How much text it can read at once. Bigger suits long documents.
Where Yi-34B ranks
Test results
GPQA Diamond
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
14.7%
What it costs in everyday terms
- 100 chats
- $0.14
- Cost of 100 chats assumes each chat sends 1,000 tokens (about 750 words) and gets 500 tokens (about 375 words) back.
- A 300-page book
- $0.09
- Cost to read a 300-page book assumes about 100,000 input tokens and no reply. A real book varies with page size and language.
- Blended price
- $0.90 per 1M
- Three parts input to one part output. Our own calculation for comparing models.
Assumptions: 100 chats of about 1,000 tokens in and 500 tokens back. a 300-page book of about 100,000 tokens, read once with no reply.
Similar models
Questions about Yi-34B
- How much does Yi-34B cost?
- Yi-34B costs $0.90 per million input tokens and $0.90 per million output tokens, using the list price from Fireworks_ai as of 26 Oct 2026. That is about $0.14 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.
- What is the context window of Yi-34B?
- Yi-34B has a context window of 4K tokens, roughly 3,000 words of text read at once. A single answer can be up to 4K tokens long.
- Is Yi-34B open source?
- Yi-34B has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.
- How good is Yi-34B compared with other AI models?
- On the Epoch Capabilities Index, Yi-34B scores 117.3 (likely range 108.9 to 120.6), which ranks 206 of 270 models we track. Scores close together are a tie in practice.
- How does Yi-34B compare with phi-3-mini 3.8B?
- On quality, neither model leads clearly across the 1 measure both have. 1 measure is too close to call. See the full comparison for every measure.
- How current are these numbers for Yi-34B?
- The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.
Where this data comes from
- Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
- LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.
Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake