1. Anthropic
mixrouter
  • mixrouter
    • mixrouter接口说明
    • 已支持的模型列表
    • 大模型官方文档
    • 已支持的模型列表
      • 语言大模型
        • OpenAI
          • embedding
          • gpt-4
          • gpt-4.1
          • gpt-4o
          • gpt-4o-mini
          • gpt-5
          • gpt-5-chat
          • gpt-5-mini
          • gpt-5-nano
          • gpt-5.1
          • gpt-5.1-chat-latest
          • gpt-5.1-codex(仅支持/v1/responses)
          • gpt-5.2
          • gpt-5.2-chat
          • gpt-5.2-pro(仅支持/v1/responses)
          • gpt-oss-120b
          • o1
          • o3
          • o3-mini
          • o3-deep-research
          • o3-pro
          • o4-mini
          • o4-mini-deep-research
        • Google
          • gemini-2.0-flash
          • gemini-2.5-computer-use-preview-10-2025
          • gemini-2.5-flash
          • gemini-2.5-flash-lite
          • gemini-2.5-flash-lite-preview
          • gemini-2.5-pro
          • gemini-3-flash-preview
          • gemini-3-pro-preview
          • gemini-robotics-er-1.5-preview
        • Anthropic
          • claude-sonnet-5
            POST
          • claude-sonnet-5(anthropic格式)
            POST
          • 通用接口
            POST
          • claude-opus-4-5-20251101
            POST
          • claude-opus-4-20250514
            POST
          • claude-sonnet-4-20250514
            POST
          • claude-sonnet-4-5-20250929
            POST
        • DeepSeek
          • deepseek-v4-pro
          • deepseek-chat
          • deepseek-reasoner
        • MiniMax
          • minimax-m2.5
          • abab6.5s-chat
          • minimax-m2
        • Moonshot
          • kimi-k2
          • kimi-k2-0711-preview
          • kimi-k2-0905
          • kimi-k2-instruct
          • kimi-k2-thinking
          • moonshot-v1-128k
          • moonshot-v1-32k
          • moonshot-v1-8k
          • moonshot-v1-128k-vision-preview
          • moonshot-v1-32k-vision-preview
          • moonshot-v1-8k-vision-preview
        • xAI
          • grok-4
          • grok-4-1-fast-non-reasoning
          • grok-4-1-fast-reasoning
        • 字节跳动
          • 通用接口
        • 智谱
          • glm-5
          • glm-5.3-flash
          • glm-4-plus
          • glm-4.5
          • glm-4.6
          • glm-4.7
        • 阿里巴巴
          • qwen3.5-122b-a10b(多模态)
          • qwen3.5-397b-a17b(多模态)
          • qwen3.6-27b
          • qwen3.6-35b-a3b
          • qwen3.5-35b-a3b
          • qwen-max
          • qwen-max-2025-01-25
          • qwen-max-latest
          • qwen-plus
          • qwen-plus-latest
          • qwen-turbo
          • qwen2.5-7b-instruct
          • qwen2.5-32b-instruct
          • qwen2.5-72b-instruct
          • qwen3-coder-plus
          • qwen3-coder-plus-2025-07-22
          • qwen3-max
          • qwen3-max-preview
          • qwen3-235b-a22b
          • qwen3-235b-a22b-instruct-2507
          • qwen3-235b-a22b-thinking-2507
          • qwen3-8b
          • qwen3-coder-30b-a3b-instruct
          • qwen3-next-80b-a3b-instruct
          • qwen3-next-80b-a3b-thinking
          • qwen-vl-max(视觉理解)
          • qwen-vl-plus(视觉理解)
          • qwen3-vl-235b-a22b-instruct(视觉理解)
          • qwen3-vl-235b-a22b-thinking(视觉理解)
        • 百度
          • ernie-x1-32k
        • 腾讯
          • hy3-preview
          • hunyuan-t1-latest
        • 讯飞
          • SparkDesk-v4.0
        • 蚂蚁
          • Ling-1T
          • Ring-1T
        • 阶跃星辰
          • step-3
      • 图片生成
        • 通用接口
          • 图片生成
          • 图片编辑
        • OpenAI
          • gpt-image系列图片生成
          • gpt-image系列图片编辑
          • dall-e-3图片生成
        • Google
          • gemini-3-pro-image-preview(google格式)
          • gemini-2.5-flash-image
          • gemini-2.5-flash-image-preview
          • gemini-3-pro-image-preview
        • Anthropic
        • BFL
          • flux-1-kontext-pro
        • ImagineArt
          • imagineart-1.5-preview
      • 音视频处理
        • OpenAI
          • gpt-4o-audio-preview
          • gpt-audio
        • 阿里巴巴
          • asr实时语音处理
          • fun-asr
          • qwen3-asr-flash
          • qwen-audio-3.0-asr-flash-filetrans
          • fun-asr-flash-2026-06-15
          • qwen3-tts-flash
        • Elevenlabs
          • eleven_v3
        • MiniMax
          • 通用接口
        • 字节火山
          • doubao-seed-asr-2.0-streaming
          • doubao-seed-asr-2.0
        • 腾讯
          • hy-asr-3.0-preview
      • 视频生成
        • Vidu
          • vidu-2.0-img2video
          • viduq2-pro提交图生视频任务
        • 字节跳动
          • 提交图生视频生成任务
          • 提交文生视频生成任务
        • 快手
          • 提交图生视频任务
          • 提交文生视频任务
        • 腾讯
          • hunyuan-video-v1.5
        • 海螺
          • 提交图生视频任务
          • 提交文生视频任务
        • sora
          • sora-2
          • sora-2-pro
        • Google
          • veo-3.1-generate-preview
          • veo-3.1-fast-generate-preview
        • 阿里巴巴
          • wan2.6-i2v
          • wan2.6-t2v
        • pixverse
          • pixverse-v5.5-t2v
          • pixverse-v5.5-i2v
      • 多模态模型
        • 智谱
          • glm-4.5v
          • glm-4.6v
        • 阿里巴巴
          • qwen2.5-omni-7b
          • qwen2.5-vl-72b-instruct
          • qwen3-omni-flash-2025-12-01
        • 日日新
          • SenseNova-V6-Pro
      • Realtime
        • OpenAI
          • gpt-4o-mini-realtime-preview
          • gpt-4o-realtime-preview
      • 向量化
        • OpenAI
          • text-embedding-3-large
          • text-embedding-3-small
          • text-embedding-ada-002
          • text-embedding-v1
    • 已支持的搜索服务
      • serper
        • get方式
        • post方式
    • gemini
      • openai格式
        • gemini-开启thinking
        • chat/completions
        • gemini-3.5-flash
      • google原生格式
        • google格式
        • gemini-3.5-flash
        • gemini-robotics-er-1.5-preview
    • anthropic
      • anthropic格式
        • tools调用
        • thinking
        • image理解
        • code_execution
      • openai格式
      • openai格式
      • anthropic格式
    • openai
      • gpt-5.2
      • openai格式
      • responses
    • deepseek
      • chat/completions
    • qwen
      • chat/completions(开启thinking)
      • 流式/chat/completions
      • qwen提交图生视频任务
    • 豆包
      • 豆包端到端实时语音
      • chat/completions
      • qwen提交文生视频任务
      • 获取视频生成任务结果
    • typesafe
      • jev
    • 获取异步任务结果
      GET
  • mixrouter
    • qwen3.5-122b-a10b(多模态)
  1. Anthropic

claude-sonnet-5

POST
https://api.mixrouter.com/v1/chat/completions

Input:Text, Images#

Output:Text#

Request

Authorization
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
Body Params application/jsonRequired

Example
{
    "model": "claude-sonnet-5",
    "max_tokens": 2000,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Summarize this article in one sentence.如何理解ai和数学的关系?十个孩子,坐大巴,20个座位,每个座位最多可以坐两个人,一共有多少总做法?"
                }
            ]
        }
    ],
    "thinking": {
        "type": "adaptive"
    },
    "steam": false
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location 'https://api.mixrouter.com/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "claude-sonnet-5",
    "max_tokens": 2000,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Summarize this article in one sentence.如何理解ai和数学的关系?十个孩子,坐大巴,20个座位,每个座位最多可以坐两个人,一共有多少总做法?"
                }
            ]
        }
    ],
    "thinking": {
        "type": "adaptive"
    },
    "steam": false
}'

Responses

🟢200OK
application/json
Bodyapplication/json

Example
{
    "id": "msg_011CfJYL2i18D7S2ZaTKzbBH",
    "model": "claude-sonnet-5",
    "object": "chat.completion",
    "created": 1790082994,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The links you meant to include didn't come through — but the math question doesn't need the article anyway.\n\nTwo things:\n\n**1. The one-sentence summary.** There's no article text in your message, so I have nothing to summarize. Paste it and I will.\n\n**2. 数学题:10 个孩子,20 个座位,每座最多 2 人。**\n\nThis is the interesting half of your message, because \"总做法\" is ambiguous, and the answer changes a lot depending on which you mean.\n\n**Interpretation A — which children end up where, treating the two children in a shared seat as an unordered pair (座位不区分左右):**\n\nChoose the split: let $k$ = number of seats holding 2 children, so $10 - k$ seats hold 1. The number of occupied seats is $10 - k$, which must be $\\le 20$ — always true for $k \\le 10$.\n\n$$\\sum_{k=0}^{5} \\frac{20!}{k!\\,(10-2k)!\\,(20-10+k)!} \\cdot \\frac{10!}{2^k}$$\n\nConcretely:\n- $k=0$: $\\binom{20}{10} \\cdot 10! = 20!/10!$\n- $k=1$: $\\binom{20}{1}\\binom{19}{8} \\cdot \\frac{10!}{2!}$\n- $k=2$: $\\binom{20}{2}\\binom{18}{6} \\cdot \\frac{10!}{2^2\\,2!}$\n- $k=3$: $\\binom{20}{3}\\binom{17}{4} \\cdot \\frac{10!}{2^3\\,3!}$\n- $k=4$: $\\binom{20}{4}\\binom{16}{2} \\cdot \\frac{10!}{2^4\\,4!}$\n- $k=5$: $\\binom{20}{5}\\binom{15}{0} \\cdot \\frac{10!}{2^5\\,5!}$\n\nNumerically: $670442572800 + 2192693028000 + 2168958480000 + 812109930000 + 123988500000 + 5951448000 = \\mathbf{6{,}000{,}947{,}488{,}800}$.\n\n**Interpretation B — same, but children sitting together in one seat are distinguishable by position (left/right 有别):**\n\nDivide by the $2^k$ factor, i.e. multiply each term by $2^k$... rather, the $2^k$ in the denominator disappears: answer $= \\mathbf{12{,}002{,}002{,}977{,}600}$ (twice A).\n\n**Interpretation C — 先分好组再安排座位, i.e. 先把 10 个孩子分成若干组(1人或2人), 再放进 20 个座位:**\n\nThat's Interpretation B: a group of 2 assigned to a seat gives an ordering, so $2^k$ orderings per grouping. Same number: $12{,}002{,}002{,}977{,}600$.\n\n**The clean way to see Interpretation B:** it equals the number of ways to place 10 labeled items into 20 labeled boxes of capacity 2. That's the coefficient of $x^{10}$ in $\\left(1 + 10x + \\frac{10\\cdot 9}{2}x^2\\right)^{20}$... more directly, $20!\\,[x^{10}]\\,(1+x+x^2/2)^{20}$ — no wait, with capacity 2 and distinguishable positions: each seat contributes $1 + 10x + \\binom{10}{2}x^2$? No — the children are being *chosen*, not pre-labeled per seat. Use exponential generating functions: seats are labeled boxes, children are labeled balls, capacity 2, so the count is\n\n$$10!\\,[x^{10}]\\left(1 + x + \\frac{x^2}{2}\\right)^{20}$$\n\nExpanding $(1+x+x^2/2)^{20} = \\sum c_n x^n$, then $10! \\cdot c_{10}$:\n\n$[x^{10}](1+x+x^2/2)^{20} = \\sum_{k} \\binom{20}{k}\\binom{20-k}{10-2k}\\frac{1}{2^k}$ where $2k \\le 10$, giving $c_{10} \\approx 3{,}310 \\ldots$ — multiply by $10! = 3628800$ → about $1.2 \\times 10^{13}$. ✓ matches $12{,}002{,}002{,}977{,}600$.\n\nNote the sanity check: total ways to seat **fewer than 20** seats used is dominated by the \"all singles\" term $20!/10! = 6.7\\times10^{11}$; the pair-heavy configurations add substantially because they spread children across more occupied seats.\n\nIf you tell me which convention your textbook/source uses (座位左右是否区分, and whether empty seats count as labeled), I'll pin it to the one exact number."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 71,
        "completion_tokens": 1574,
        "total_tokens": 1645,
        "usage_semantic": "openai",
        "usage_source": "anthropic",
        "billing_usage": {
            "source": "claude_messages",
            "semantic": "anthropic",
            "claude_usage": {
                "input_tokens": 71,
                "cache_creation_input_tokens": 0,
                "cache_read_input_tokens": 0,
                "output_tokens": 1574,
                "cache_creation": {},
                "claude_cache_creation_5_m_tokens": 0,
                "claude_cache_creation_1_h_tokens": 0
            }
        },
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "video_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "reasoning_tokens": 0
        },
        "input_tokens": 71,
        "output_tokens": 0,
        "input_tokens_details": null,
        "claude_cache_creation_5_m_tokens": 0,
        "claude_cache_creation_1_h_tokens": 0
    }
}
Modified at 2026-09-22 12:47:42
Previous
gemini-robotics-er-1.5-preview
Next
claude-sonnet-5(anthropic格式)
Built with