AI 模型情报

对比 · 2026-06-29

Gemini 2.5 Pro vs Claude Sonnet 4.5 (latest)

并排对比 Gemini 2.5 Pro(Google)与 Claude Sonnet 4.5 (latest)(Anthropic)的定价、上下文窗口与能力。 侧重:long context。

Gemini 2.5 ProClaude Sonnet 4.5 (latest)
厂商GoogleAnthropic
输入价格 / 1M token$1.25$3.00
输出价格 / 1M token$10.00$15.00
1M token 合计(输入 + 输出)$11.25$18.00
上下文长度1.05M200K
最大输出 token66K64K
工具调用
结构化输出未公开
推理
图像输入
开放权重
渠道可用性28 家渠道21 家渠道
发布日期2025-06-172025-09-29
知识截止2025-012025-07-31

一句话结论

  • Gemini 2.5 Pro 在每百万 token(输入 + 输出合计)成本上便宜约 1.6 倍。
  • Gemini 2.5 Pro 的上下文窗口更长(1.05M,对比 200K)。
  • 仅 Gemini 2.5 Pro 支持结构化输出 / JSON 模式。
  • Gemini 2.5 Pro 在更多提供商处可用(28 家 vs 21 家)。
Gemini 2.5 Pro · 查看全部 28 家渠道 →Claude Sonnet 4.5 (latest) · 查看全部 21 家渠道 →

How to read this comparison

This page compares Gemini 2.5 Pro and Claude Sonnet 4.5 (latest) on the dimensions that matter most for production LLM selection: per-token cost, context window, declared capabilities (tool calling, structured output, reasoning, vision), and provider availability.

Green highlights in the table indicate which model leads on a given row. "Leads" means lower price or higher context/capability — not necessarily "better for your use case". A model that costs 3× more may still be the right choice if it unlocks a capability you need.

What this comparison does NOT tell you

  • Quality / accuracy — we have no benchmark data. Declared capabilities ≠ measured performance.
  • Latency — time-to-first-token varies by provider, region and load. Test with your actual traffic.
  • Prompt caching savings — if you reuse system prompts, the cheaper model on headline rate may not be cheapest in practice.
  • Fine-tuning availability — not all models can be fine-tuned, even if they are open-weight.

Data is refreshed daily. If a model's capabilities or pricing change, this page updates automatically on the next build cycle.

Frequently asked questions

Gemini 2.5 Pro 是否比 Claude Sonnet 4.5 (latest) 便宜?

Gemini 2.5 Pro 的输入价为 $1.25/百万 token + 输出价为 $10.00/百万 token;Claude Sonnet 4.5 (latest) 为 $3.00/百万 token(输入)+ $15.00/百万 token(输出)。综合每百万 token 成本更低的是 Gemini 2.5 Pro。

Gemini 2.5 Pro 与 Claude Sonnet 4.5 (latest) 谁的上下文更长?

Gemini 2.5 Pro 的上下文窗口更长——约 1,048,576 token vs 200,000 token。

在哪里可以运行 Gemini 2.5 Pro 和 Claude Sonnet 4.5 (latest)?

Gemini 2.5 Pro 在 28 家提供商可用;Claude Sonnet 4.5 (latest) 在 21 家提供商可用。完整列表请参见各模型详情页。

最近更新:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.