补全 20 行函数的模型和读半个 monorepo 再调工具的模型，根本不是同一类产品。输出贵，工具调用会以无聊的方式失败，长上下文也烧钱。用这页先定主编码模型和更便宜的兜底，再定预算，别让 Agent 无人看管时跑飞。
来源依据: NextModel 用例分类以及可用时的 OpenRouter 支持参数元数据。 · 更新日期 2026-07-01
步骤
匹配分
先从候选名单开始，再用真实提示词测试，并在接入生产路由前比较月度成本。
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
比较表
缩小生产候选、建立兜底策略或比较模型经济性时用。
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | $1 / 1M tokens | $5 / 1M tokens | 200k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | 200k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | $3 / 1M tokens | $15 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Anthropic: Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Anthropic | $3 / 1M tokens | $15 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| FLUX.2 Flexblack-forest-labs/FLUX.2-flex | Black Forest Labs | $0.2 / image | — | — | StreamingVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| FLUX.2 PROblack-forest-labs/FLUX.2-pro | Black Forest Labs | $0.075 / image | — | — | StreamingVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Deepseek V3.2 CNdeepseek/deepseek-v3.2-cn | DeepSeek | $0.29 / 1M tokens | $0.44 / 1M tokens | — | Streaming | Chinese Q&A, general chat | 1000-3000ms | Catalog | Platform curated |
常见问题
工具调用稳、结构化输出靠谱、上下文够你塞的那截仓库、指令跟得住。单看 token 价没有意义。
按项目设预算，盯输出 token，简单任务走便宜模型，质量不过再升级。
指南