DeepSeek R1 0528 Qwen3 8B: pricing, context and performance

What you need to know

Released on May 29, 2025, DeepSeek R1 0528 Qwen3 8B is one of the 8 DeepSeek models tracked on this site. It is an open-weight model: you can host it yourself on infrastructure you control, and 1 API providers listed on models.dev also offer it. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it more than a year old: successors may have shipped since.

We file it under open-weight models (68 models in this category on the site).

What it costs

DeepSeek R1 0528 Qwen3 8B costs $0.06 per million input tokens and $0.09 per million output tokens (median of 1 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.001, or $1.38 for 1,000 such tasks.

That is 11.1 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

What do independent benchmarks say?

Epoch AI publishes 2 results for DeepSeek R1 0528 Qwen3 8B on our basket's benchmarks: too few to compute a reliable capability index.

• GPQA Diamond (PhD-level science questions): 9.3% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 43.9% — the best tracked model, GPT-5.5 Pro, reaches 100%

What it can do

Its context window reaches 128,000 tokens, roughly 192 pages of text at 500 words per page: enough for a medium-length document. A single answer can run to 32,000 tokens.

It accepts as input: text.

It is not listed as able to call tools, so it is a poor fit for driving an agent that has to act on other software.

Who is it for?

Given its category, DeepSeek R1 0528 Qwen3 8B is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Comparable models

In the same category, the models closest to DeepSeek R1 0528 Qwen3 8B are:

• Ministral 3 3B 2512 (Mistral AI, $0.10 per million output tokens)
• Mistral Small 3 (Mistral AI, $0.08 per million output tokens)
• Granite 4.0 Micro (IBM (Granite), $0.11 per million output tokens)
• LFM2-24B-A2B (Liquid AI, $0.12 per million output tokens)