Claude Sonnet 5 vs DeepSeek V4 Pro
API pricing, context window and capabilities for Claude Sonnet 5 and DeepSeek V4 Pro, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersClaude Sonnet 5 wins on coding and on intelligence. DeepSeek V4 Pro wins on price.
Price
DeepSeek V4 Pro
Coding
Claude Sonnet 5
Intelligence
Claude Sonnet 5
Context window
Tied
Key takeaways
who wins on what, from the published numbersClaude Sonnet 5 wins
- Supports vision
DeepSeek V4 Pro wins
- Cheaper input ($2.00 vs $0.43 /1M)
- Cheaper output ($10.00 vs $0.87 /1M)
- Higher max output (128K vs 384K)
Cheaper overall
DeepSeek V4 Pro
$0.43 + $0.87 /1M
Larger context
Tied
More providers
Tied
Pricing & specs
cheapest serving route · per 1M tokens| Claude Sonnet 5 | DeepSeek V4 Pro | |
|---|---|---|
| Input $/1M | $2.00 | $0.43 best |
| Output $/1M | $10.00 | $0.87 best |
| Context window | 1M | 1M |
| Max output | 128K | 384K best |
| Serving providers | 4 | 4 |
| Released | 2026-06-30 | 2026-04-24 |
Benchmarks
Artificial Analysis indices, side by side| Claude Sonnet 5 | DeepSeek V4 Pro | |
|---|---|---|
| Intelligence | 53.4 best | 44.3 |
| Coding | 71.5 best | 59.4 |
| GPQA Diamond | 91% best | 89% |
| Output speed | 67 t/s | 75 t/s best |
| Latency (TTFT) | 42.19s | 7.80s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Claude Sonnet 5
via Amazon Bedrock
$20
DeepSeek V4 Pro
via Tencent
$3.04
Capabilities
feature support, side by side| Feature | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| Vision | ✓ | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, Claude Sonnet 5 or DeepSeek V4 Pro?
DeepSeek V4 Pro is cheaper for input ($2.00 vs $0.43 per 1M tokens). DeepSeek V4 Pro is cheaper for output ($10.00 vs $0.87 per 1M tokens).
What is the context window difference between Claude Sonnet 5 and DeepSeek V4 Pro?
Both Claude Sonnet 5 and DeepSeek V4 Pro have about a 1M-token context window.
How do Claude Sonnet 5 and DeepSeek V4 Pro compare on benchmarks?
On the tracked Artificial Analysis indices, Claude Sonnet 5 leads on coding, and Claude Sonnet 5 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