An earlier DeepSeek flagship against Alibaba's trillion-parameter reasoner.
DeepSeek V4 Pro 0423 and Qwen3.8 2.4T are text-only flagships with a million-token window, tool support and zero-retention terms. One is an earlier DeepSeek Pro snapshot; the other is Alibaba's newest trillion-parameter reasoning model.
The 0423 snapshot has 1.6 trillion parameters and a $2.09 price, tuned for advanced reasoning and coding. Qwen3.8 2.4T has 2.4 trillion parameters with 95B active per token and a $6.00 price, tuned for heavyweight reasoning. The price gap is the first thing to notice.
At a glance
| Spec | DeepSeek V4 Pro 0423 | Qwen3.8 2.4T |
|---|---|---|
| Maker | DeepSeek | Alibaba |
| Parameters | 1.6T | 2.4T |
| Active per token | — | 95B |
| Context window | 1M (750,000 words) | 1M (750,000 words) |
| Upstream price / MTok | $2.09 | $6.00 |
| Image input | No | No |
| Tool use | Yes | Yes |
| Zero data retention | Yes | Yes |
| License | MIT | Apache 2.0 |
| Good at | Advanced reasoning and coding | Heavyweight reasoning |
Where DeepSeek V4 Pro 0423 pulls ahead
- Price: $2.09 versus $6.00 per million tokens, about 65% cheaper.
- The same million-token window and zero-retention terms at a much lower rate.
- Advanced reasoning and coding without paying flagship Qwen prices.
Where Qwen3.8 2.4T pulls ahead
- A larger model at 2.4 trillion parameters, with 95B active per token.
- The newer release, aimed at the heaviest reasoning workloads.
- More capacity when a problem genuinely needs the largest Qwen.
The price difference
Qwen3.8 2.4T costs $6.00 per million tokens against $2.09 for DeepSeek V4 Pro 0423 — about 2.9x more. On UsingOpen you can chat with both for free inside the daily limit, so the rate is a fair proxy for how expensive each model is to run rather than a bill you pay here. Multiply it by your monthly token volume if you are comparing API access elsewhere.
Which should you choose?
DeepSeek V4 Pro 0423 is the value pick of the pair: a 1.6T reasoning model with the same million-token window for about a third of Qwen's price. For most text reasoning and coding, start here.
Qwen3.8 2.4T makes sense when the task is at the top end and the larger model shows a real quality gain. At $6.00 per million tokens, that gain needs to be measurable on your own prompts.
Test both models with the same prompt
Rather than relying on parameter counts or catalog blurbs alone, test both models directly in side-by-side Compare mode on a representative task:
Test DeepSeek V4 Pro 0423 and Qwen3.8 2.4T side-by-side in Compare mode →
Here is an evaluation prompt you can paste into both:
Review this code change.
1. Identify concrete correctness bugs.
2. Separate confirmed bugs from possible risks.
3. Give a minimal failing example for each confirmed bug.
4. Suggest the smallest safe correction.
5. State what you could not verify.
Test both in Compare mode · Chat with DeepSeek V4 Pro 0423 · Chat with Qwen3.8 2.4T
Frequently asked questions
Do DeepSeek V4 Pro 0423 and Qwen3.8 2.4T have the same context window?
Yes — both are listed with a 1M context window, roughly 750,000 words. The practical limit is therefore similar, and the decision comes down to price, modalities and behaviour.
Can DeepSeek V4 Pro 0423 or Qwen3.8 2.4T read images?
Neither model accepts images — both are text-only. A visual task needs a multimodal model such as Qwen3.8 Flash, GLM 5.3 Flash or Gemma 4 instead.
How should I compare DeepSeek V4 Pro 0423 and Qwen3.8 2.4T for coding?
Test both on the same representative task: a bug fix, code review or refactor. Check correctness, instruction following and the amount of manual repair needed. The catalog descriptions and parameter counts do not establish which model performs better on your code.
Which is cheaper, DeepSeek V4 Pro 0423 or Qwen3.8 2.4T?
DeepSeek V4 Pro 0423 is listed at $2.09 per million tokens against $6.00 for Qwen3.8 2.4T — about 65% lower cost (Qwen3.8 2.4T costs roughly 2.9 times as much). Both are free to chat with on UsingOpen inside the daily limit when live; the rates matter if you are comparing what API access would cost.
Can I chat with DeepSeek V4 Pro 0423 and Qwen3.8 2.4T for free?
Yes. Both are selectable on UsingOpen without an account when they are live, and each user gets 10 free prompts per day. A model paused for capacity is unavailable until it returns; the picker shows live status. History stays on your device, and Compare mode can send one prompt to both models side by side.
Should I use DeepSeek V4 Pro 0423 or the newer DeepSeek V4 Pro?
The newer release — the 0813 snapshot listed as DeepSeek V4 Pro — is the full-strength V4 and costs slightly less at $1.98 per million tokens. The 0423 snapshot is the April release, kept for anyone comparing the two.
Do either of these models read images?
No. Both are text-only. If you need a DeepSeek model with vision, choose DeepSeek V4.1 Flash; for Alibaba, choose Qwen3.8 Flash.
Related comparisons
- DeepSeek V4.1 Flash vs DeepSeek V4 Flash — DeepSeek's new multimodal Flash against the older text-only bargain.
- Qwen3.8 2.4T vs Kimi K3 — The two trillion-parameter flagships: Qwen's text heavyweight against Kimi's multimodal giant.
- GLM 5.2 vs GLM 5.3 — Two generations of Z.ai's long-work model, with a price gap and a capacity catch.
All models · Coding models · Compare models · Free AI chat · FAQ