Qwen3-1.7B
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
text → text · made by Alibaba
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Fireworks AI aggregator | standard | $0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Featherless AI aggregator | standard | $0.32per Mtok in$1.6per Mtok outapi.featherless.ai · read 2026-09-20 |
Measured 2 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 257thof 306 | OTIS Mock AIME 2024-2025 | mean_score (none) | 8.056 |
| 284thof 326 | GPQA Diamond | mean_score | 38.005 |
About
Qwen3-1.7B — a text model from Alibaba, sold by 2 companies from $0.1 in and $0.1 out per million tokens, placed 257th of 306 on OTIS Mock AIME 2024-2025.
It takes text and returns text, with a context window of 32,768 tokens. It was published in April 2025. The catalogue files it under reasoning. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest. Two companies sell it. The cheapest is $0.1 in and $0.1 out per million tokens at Fireworks AI. It has been measured on 2 boards, and stands best at 257th of 306 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Published
- April 2025
- Parameters
- 2 billion · read from its own weights
- Licence
- apache-2.0
- Sellers
- 2
- Maker's own price
- not read
- Price
- $0.1 in and $0.1 out per million tokens — Fireworks AI
- Boards
- 2
- Best place
- 257th of 306 — OTIS Mock AIME 2024-2025
Known as 7 names
Qwen/Qwen3-1.7BPrimeIntellect/Qwen3-1.7BTnt3o5/qwen3-1-7bVityaVitalich/Qwen3-1.7Bggbetz/Qwen3-1.7Bunsloth/Qwen3-1.7Bwillcb/Qwen3-1.7B