DeepSeek V4 Pro 0423 vs Qwen3.5 397B A17B
API pricing, context window and capabilities for DeepSeek V4 Pro 0423 and Qwen3.5 397B A17B, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersDeepSeek V4 Pro 0423 wins on Terminal-Bench, on intelligence and on context window.
Price
Tied
Terminal-Bench
DeepSeek V4 Pro 0423
Intelligence
DeepSeek V4 Pro 0423
Context window
DeepSeek V4 Pro 0423
Key takeaways
who wins on what, from the published numbersDeepSeek V4 Pro 0423 wins
- Cheaper output ($0.87 vs $0.986 /1M)
- Larger context window (1M vs 262K)
- Higher max output (1M vs 262K)
- More serving providers (16 vs 7)
Qwen3.5 397B A17B wins
- Cheaper input ($0.435 vs $0.164 /1M)
- Supports vision
- Has web search
Cheaper overall
Qwen3.5 397B A17B
$0.164 + $0.986 /1M
Larger context
DeepSeek V4 Pro 0423
1M
More providers
DeepSeek V4 Pro 0423
16 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| DeepSeek V4 Pro 0423 | Qwen3.5 397B A17B | |
|---|---|---|
| Input $/1M | $0.435via Tencent | $0.164via Aihubmix best |
| Output $/1M | $0.87via Tencent best | $0.986via Aihubmix |
| Context window | 1M best | 262K |
| Max output | 1M best | 262K |
| Serving providers | 16 best | 7 |
| Date | Released Apr 24, 2026 | Released Feb 16, 2026 |
Benchmarks
Benchmark scores, side by side| DeepSeek V4 Pro 0423 | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence | 30.4 best | 18.4 |
| Terminal-Bench | 65% best | 51% |
| GPQA Diamond | 89% | 89% |
| Output speed | 100 t/s best | 56 t/s |
| Latency (TTFT) | 1.64s best | 2.44s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
DeepSeek V4 Pro 0423
via Tencent
$3.04
Qwen3.5 397B A17B
via Aihubmix
$1.81
Capabilities
feature support, side by side| Feature | DeepSeek V4 Pro 0423 | Qwen3.5 397B A17B |
|---|---|---|
| Vision | — | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro 0423 or Qwen3.5 397B A17B?
Qwen3.5 397B A17B is cheaper for input ($0.435 vs $0.164 per 1M tokens) from Aihubmix. DeepSeek V4 Pro 0423 is cheaper for output ($0.87 vs $0.986 per 1M tokens) from Tencent.
What is the context window difference between DeepSeek V4 Pro 0423 and Qwen3.5 397B A17B?
DeepSeek V4 Pro 0423 has a 1M-token context window and Qwen3.5 397B A17B has 262K tokens, so DeepSeek V4 Pro 0423 can take a larger prompt.
How do DeepSeek V4 Pro 0423 and Qwen3.5 397B A17B compare on benchmarks?
On the tracked benchmarks, DeepSeek V4 Pro 0423 leads on Terminal-Bench, and DeepSeek V4 Pro 0423 leads on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI