跳到主要内容

DeepSeekLLM

DeepSeek V4.1 Flash API

模型 IDdeepseek/deepseek-v4.1-flash

DeepSeek V4.1 Flash through the Hermes chat catalog.

  • 1.05M context
  • 工具
  • 视觉
  • 推理
  • JSON

在 Playground 中运行 DeepSeek V4.1 Flash

Send a chat request with your account and see the exact token charge. Code needs an API key.

参数

模型
model
deepseek/deepseek-v4.1-flash
messages[].content
messages[0].content
max_tokens
temperature

请求预览

{"model": "deepseek/deepseek-v4.1-flash","messages": [],"stream": true,"max_tokens": 1024}

网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。

结果

发送一条消息,用你的账号运行 DeepSeek V4.1 Flash。

收到回复后,这里会显示用量和扣费。

DeepSeek V4.1 Flash 价格

美元 / 百万 token。按每次请求的提示词长度选择档位。

正在加载价格…
  1. Reserve请求被接受时,Hermes 会按估算的提示词长度加上 max_tokens(未设置时为 8,192)预留额度。设置 max_tokens 可以减少预留。
  2. Settle响应结束后,按模型返回的实际用量结算:提示词 token 按输入价、命中缓存的 token 按缓存读取价、输出 token 按输出价,预留的剩余部分立即释放。
  3. Failures模型拒绝请求时不收费。流式输出在已生成内容后中断时,会按已生成文本估算并扣费。

DeepSeek V4.1 Flash 能做什么

DeepSeek describes V4.1 Flash as a model with native visual understanding. Its current changelog says its own API retired the earlier V4 Flash and V4 Flash Vision Exp models and temporarily routes their names to V4.1 Flash. That manufacturer routing statement does not prove how a separate Hermes upstream channel is mapped.

The Hermes catalog lists deepseek/deepseek-v4.1-flash with a 1,048,576-token context. Vision is listed for this specific Hermes entry. Check its current status, request capabilities and token price before use.

使用场景

  1. Analyze text or code

    Evaluate model behavior on your own workload.

  2. Build tool workflows

    Handle tool calls and validate results in your application.

  3. Work with long inputs

    Stay within the channel's listed context, leaving room for output.

用代码调用 DeepSeek V4.1 Flash

任意 OpenAI SDK 都可用:设置 base URL 和你的 Hermes Key。

  1. 1

    创建 API Key

    In the dashboard, with the chat:create scope. API 密钥
  2. 2

    Point your SDK at Hermes

    Base URL https://api.hermes-ai.net/api/v1
  3. 3

    发送对话补全请求

    POST /chat/completions with deepseek/deepseek-v4.1-flash

代码示例

Set HERMES_API_KEY in your environment.

shell
export HERMES_API_KEY=your_api_key
Full chat API reference
curl https://api.hermes-ai.net/api/v1/chat/completions \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "max_tokens": 200
  }'

请求

POST https://api.hermes-ai.net/api/v1/chat/completions 带 chat:create 权限的 API Key,或已登录会话。

字段类型说明
modelstringdeepseek/deepseek-v4.1-flash
messagesarrayOpenAI 对话消息:system、user、assistant、tool 角色;text 和 image_url 内容块。
streambooleanSSE 流式输出,最后一个事件包含 usage。
max_tokensinteger输出上限,同时决定预留额度。
tools / tool_choicearray / object仅支持 function 工具。
response_formatobject模型支持时可用 JSON 模式和 JSON schema。
temperature, top_p, stop, seed, reasoning_effort原样透传。

响应

字段说明
choices[].message / deltaOpenAI chat completion 结构。
usage模型返回的 prompt_tokens、completion_tokens 和 prompt_tokens_details.cached_tokens。
hermes.charged_micros精确扣费(微美元,JSON 响应)。流式请求可在 GET /api/v1/chat/requests 查看。
x-hermes-request请求 id 响应头,账单流水中使用同一 id。
error.code文档中的 Hermes 错误码;请按错误码而非消息文本分支。

DeepSeek V4.1 Flash API 常见问题

Answers built from the model's catalog entry and the Hermes AI API contract.

Does DeepSeek's alias migration guarantee the same routing on Hermes?

No. The cited migration describes DeepSeek's own API. A third-party route can have different model mapping and capabilities; check the exact Hermes entry.

What is the DeepSeek V4.1 Flash API on Hermes AI?

DeepSeek V4.1 Flash by DeepSeek is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID deepseek/deepseek-v4.1-flash.

What is the context window of DeepSeek V4.1 Flash?

1,048,576 tokens, shared by the prompt and the output.

Does DeepSeek V4.1 Flash support vision, tools and JSON output?

Supported: 工具, 视觉, 推理 和 JSON. Not supported: 音频. Streaming works with stream: true.

How is DeepSeek V4.1 Flash billed?

Per token, from prepaid credits. When a request is accepted, credits are reserved for the estimated prompt plus max_tokens of output (8,192 when you set none); when it finishes, the exact charge is taken from the usage the model reports and the rest is released. A rejected request is not charged. Rates are in the pricing table.

Can I use the OpenAI SDK with DeepSeek V4.1 Flash?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send deepseek/deepseek-v4.1-flash as the model. Chat completions, streaming, tools and JSON output work unchanged.

What happens when I hit a rate limit?

Too many requests per minute return 429 RATE_LIMITED and too many in flight return 429 CONCURRENCY_LIMITED. If the model provider rate limits, you get 429 UPSTREAM_RATE_LIMITED and nothing is charged. Retry with backoff.

How do I get an API key for DeepSeek V4.1 Flash?

Create one under API 密钥 in the dashboard with the chat:create scope, then add credits on the Billing page.