claude-sonnet-4-6 vs deepseek-v4-pro-0813
Side-by-side comparison of claude-sonnet-4-6 and deepseek-v4-pro-0813: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. deepseek-v4-pro-0813 outperforms claude-sonnet-4-6 on 4 of 4 shared benchmarks.
claude-sonnet-4-6
Input / 1M
$3.00
Output / 1M
$15.00
Context
1M
Model ID
anthropic/claude-sonnet-4-6
deepseek-v4-pro-0813
Input / 1M
$1.32
Output / 1M
$3.96
Context
1M
Model ID
deepseek/deepseek-v4-pro-0813
Benchmark comparison
Intelligence Indexreasoning
claude-sonnet-4-638.5%
deepseek-v4-pro-081342.1%
Coding Indexcoding
claude-sonnet-4-663.0%
deepseek-v4-pro-081368.8%
GPQA Diamondreasoning
claude-sonnet-4-687.5%
deepseek-v4-pro-081392.8%
Terminal-Bench Hardagentic
claude-sonnet-4-653.0%
deepseek-v4-pro-0813N/A
τ²-Benchagentic
claude-sonnet-4-675.7%
deepseek-v4-pro-0813N/A
SciCodecoding
claude-sonnet-4-6N/A
deepseek-v4-pro-081351.0%
Humanity's Last Examreasoning
claude-sonnet-4-633.6%
deepseek-v4-pro-081341.0%
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
| claude-sonnet-4-6 | deepseek-v4-pro-0813 | |
|---|---|---|
| Input price / 1M | $3.00 | $1.32 |
| Output price / 1M | $15.00 | $3.96 |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 384K tokens |
| Vision input | Yes | N/A |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Computer use | Yes | N/A |
| Provider | Anthropic PBC | DeepSeek |
Questions people ask
Is claude-sonnet-4-6 better than deepseek-v4-pro-0813?
deepseek-v4-pro-0813 outperforms claude-sonnet-4-6 on 4 of 4 shared benchmarks. See the benchmark comparison above for specifics: claude-sonnet-4-6 and deepseek-v4-pro-0813 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, claude-sonnet-4-6 or deepseek-v4-pro-0813?
deepseek-v4-pro-0813 is cheaper. claude-sonnet-4-6 costs $3.00/$15.00 per 1M input/output tokens, while deepseek-v4-pro-0813 costs $1.32/$3.96.
Can I use claude-sonnet-4-6 and deepseek-v4-pro-0813 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "anthropic/claude-sonnet-4-6" and "deepseek/deepseek-v4-pro-0813", no other code changes needed.
What are the context windows?
claude-sonnet-4-6 supports up to 1M tokens of context. deepseek-v4-pro-0813 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 claude-sonnet-4-6 and deepseek-v4-pro-0813 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.