deepseek-v4-pro-0813 vs claude-sonnet-4-5
Side-by-side comparison of deepseek-v4-pro-0813 and claude-sonnet-4-5: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API.
deepseek-v4-pro-0813
Input / 1M
$1.32
Output / 1M
$3.96
Context
1M
Model ID
deepseek/deepseek-v4-pro-0813
claude-sonnet-4-5
Input / 1M
$3.00
Output / 1M
$15.00
Context
1M
Model ID
vertex/claude-sonnet-4-5
Benchmark comparison
Intelligence Indexreasoning
deepseek-v4-pro-081323.1%
claude-sonnet-4-5N/A
GPQA Diamondreasoning
deepseek-v4-pro-081388.8%
claude-sonnet-4-5N/A
Terminal-Bench Hardagentic
deepseek-v4-pro-081346.2%
claude-sonnet-4-5N/A
τ²-Benchagentic
deepseek-v4-pro-081396.2%
claude-sonnet-4-5N/A
SciCodecoding
deepseek-v4-pro-081350.0%
claude-sonnet-4-5N/A
Humanity's Last Examreasoning
deepseek-v4-pro-081335.9%
claude-sonnet-4-5N/A
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| deepseek-v4-pro-0813 | claude-sonnet-4-5 | |
|---|---|---|
| Input price / 1M | $1.32 | $3.00 |
| Output price / 1M | $3.96 | $15.00 |
| Context window | 1M tokens | 1M tokens |
| Max output | 384K tokens | 64K tokens |
| Vision input | N/A | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | N/A |
| Prompt caching | Yes | Yes |
| Computer use | N/A | Yes |
| Provider | DeepSeek | Google Vertex AI |
Questions people ask
Is deepseek-v4-pro-0813 better than claude-sonnet-4-5?
Benchmark data is limited for one or both models. Compare pricing and capabilities in the tables above, and test both on your own workload.
Which is cheaper, deepseek-v4-pro-0813 or claude-sonnet-4-5?
deepseek-v4-pro-0813 is cheaper. deepseek-v4-pro-0813 costs $1.32/$3.96 per 1M input/output tokens, while claude-sonnet-4-5 costs $3.00/$15.00.
Can I use deepseek-v4-pro-0813 and claude-sonnet-4-5 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "deepseek/deepseek-v4-pro-0813" and "vertex/claude-sonnet-4-5", no other code changes needed.
What are the context windows?
deepseek-v4-pro-0813 supports up to 1M tokens of context. claude-sonnet-4-5 supports up to 1M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between deepseek-v4-pro-0813 and claude-sonnet-4-5 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.