How much does Qwen2.5-Coder-3B cost?

Qwen2.5-Coder-3B costs $0.055 per million input tokens and $0.065 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about less than $0.01 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 Qwen2.5-Coder-3B?

Qwen2.5-Coder-3B has a context window of 33K tokens, roughly 25,000 words of text read at once. A single answer can be up to 33K tokens long.

Is Qwen2.5-Coder-3B open source?

We list Qwen2.5-Coder-3B as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "Unknown").

How good is Qwen2.5-Coder-3B compared with other AI models?

On the Epoch Capabilities Index, Qwen2.5-Coder-3B scores 107.5 (likely range 93.3 to 114.9), which ranks 230 of 270 models we track. Scores close together are a tie in practice.

How does Qwen2.5-Coder-3B compare with Nemotron-4 15B?

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 Qwen2.5-Coder-3B?

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.

AI Rankings

Qwen2.5-Coder-3B: Score, Price and Context Window

Where Qwen2.5-Coder-3B from Alibaba ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

Alibaba
Closed weights
Released Sep 2024

Its score range overlaps with Phi-2, the model just above it, so a small gap in rank is not a meaningful difference.

Skip if

Cutting-edge tasks: its overall Epoch score is in the lower part of the models we track.

These lines are worked out from the numbers on this page, not from hands-on testing.

Key facts

Overall score: 107.5; Rank 230 of 270. Likely range 93.3 to 114.9.
Price per million tokens: $0.055 in / $0.065 out; Blended $0.058. Median across hosting providers, checked 26 Oct 2026.
Context window: 33K tokens; About 25,000 words at once. One answer up to 33K tokens.
Weights: Closed; Used through the maker's apps or API (Epoch AI: Unknown).

We do not have an Arena human-vote rating and benchmark results for Qwen2.5-Coder-3B yet. It is shown as "Not measured" rather than guessed.

Try itQwen Studio in our AI tools directoryQwen assistant for chat, document processing, multimodal questions, web search, and creative tasks.

How Qwen2.5-Coder-3B stacks up

Each strip shows every model we track as faint bars. The dot is this model. Better is always to the right, even for price.

Qwen2.5-Coder-3B compared with all models we trackOverall capability: 107.5. Better than 14% of the other 269 models. Price: $0.058 per 1M. Cheaper than 99% of the other 200 priced models. Context window: 33K tokens. Larger context window than 10% of the other 198 models.

Overall capability107.5
Better than 14% of the other 269 models
Epoch Capabilities Index: one score that combines many tests.
Price$0.058 per 1M
Cheaper than 99% of the other 200 priced modelsTop 10%
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window33K tokens
Larger context window than 10% of the other 198 models
How much text it can read at once. Bigger suits long documents.

Compared with the other published models that have each measure. Data updated 26 Oct 2026.

Where Qwen2.5-Coder-3B ranks

Leaderboards it appears on, best placing first.

See all leaderboards

What it costs in everyday terms

List prices turned into amounts you can picture. Real bills depend on how you use it.

100 chats: less than $0.01; 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: less than $0.01; 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: $0.058 per 1M; Three parts input to one part output. Our own calculation for comparing models.

Similar models

Models from other makers with a similar overall score.

Learn more

Questions about Qwen2.5-Coder-3B

How much does Qwen2.5-Coder-3B cost?: Qwen2.5-Coder-3B costs $0.055 per million input tokens and $0.065 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about less than $0.01 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 Qwen2.5-Coder-3B?: Qwen2.5-Coder-3B has a context window of 33K tokens, roughly 25,000 words of text read at once. A single answer can be up to 33K tokens long.
Is Qwen2.5-Coder-3B open source?: We list Qwen2.5-Coder-3B as closed: it is used through its maker's apps or API and its weights are not published (Epoch AI lists its access as "Unknown").
How good is Qwen2.5-Coder-3B compared with other AI models?: On the Epoch Capabilities Index, Qwen2.5-Coder-3B scores 107.5 (likely range 93.3 to 114.9), which ranks 230 of 270 models we track. Scores close together are a tie in practice.
How does Qwen2.5-Coder-3B compare with Nemotron-4 15B?: 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 Qwen2.5-Coder-3B?: 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