DeepSeek V4 Pro vs Qwen3.5 397B A17B
API pricing, context window and capabilities for DeepSeek V4 Pro and Qwen3.5 397B A17B, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersDeepSeek V4 Pro wins on price, on coding, on intelligence and on context window.
Price
DeepSeek V4 Pro
Coding
DeepSeek V4 Pro
Intelligence
DeepSeek V4 Pro
Context window
DeepSeek V4 Pro
Key takeaways
who wins on what, from the published numbersDeepSeek V4 Pro wins
- Cheaper input ($0.43 vs $0.60 /1M)
- Cheaper output ($0.87 vs $3.60 /1M)
- Larger context window (1M vs 262K)
- Higher max output (384K vs 66K)
- More serving providers (4 vs 3)
- Supports prompt caching
Qwen3.5 397B A17B wins
- Supports vision
Cheaper overall
DeepSeek V4 Pro
$0.43 + $0.87 /1M
Larger context
DeepSeek V4 Pro
1M
More providers
DeepSeek V4 Pro
4 providers
Pricing & specs
cheapest serving route · per 1M tokens| DeepSeek V4 Pro | Qwen3.5 397B A17B | |
|---|---|---|
| Input $/1M | $0.43 best | $0.60 |
| Output $/1M | $0.87 best | $3.60 |
| Context window | 1M best | 262K |
| Max output | 384K best | 66K |
| Serving providers | 4 best | 3 |
| Released | 2026-04-24 | 2026-02-16 |
Benchmarks
Artificial Analysis indices, side by side| DeepSeek V4 Pro | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence | 44.3 best | 33.7 |
| Coding | 59.4 best | 48.2 |
| GPQA Diamond | 89% | 89% |
| Output speed | 75 t/s best | 61 t/s |
| Latency (TTFT) | 7.80s best | 9.37s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
DeepSeek V4 Pro
via Tencent
$3.04
Qwen3.5 397B A17B
via OpenRouter
$6.60
Capabilities
feature support, side by side| Feature | DeepSeek V4 Pro | 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 or Qwen3.5 397B A17B?
DeepSeek V4 Pro is cheaper for input ($0.43 vs $0.60 per 1M tokens). DeepSeek V4 Pro is cheaper for output ($0.87 vs $3.60 per 1M tokens).
What is the context window difference between DeepSeek V4 Pro and Qwen3.5 397B A17B?
DeepSeek V4 Pro has a 1M-token context window and Qwen3.5 397B A17B has 262K tokens, so DeepSeek V4 Pro can take a larger prompt.
How do DeepSeek V4 Pro and Qwen3.5 397B A17B compare on benchmarks?
On the tracked Artificial Analysis indices, DeepSeek V4 Pro leads on coding, and DeepSeek V4 Pro leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI