本文へスキップ

DeepSeekLLM

DeepSeek V4 Flash API

Model IDdeepseek/deepseek-v4-flash

DeepSeek V4 Flash through the Hermes chat catalog.

  • 1.05M context
  • ツール
  • JSON

プレイグラウンドで DeepSeek V4 Flash を実行

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

パラメーター

モデル
model
deepseek/deepseek-v4-flash
messages[].content
messages[0].content
max_tokens
temperature

リクエストのプレビュー

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

Web Playground はサインイン中のセッションでこのボディを送信します。コードからは同じボディを API キーとともに送信してください。

結果

Send a message to run DeepSeek V4 Flash with your account.

Usage and charge appear here after a reply.

DeepSeek V4 Flash の料金

USD per 1M tokens. The tier is chosen by the prompt size of each request.

料金を読み込み中…
  1. ReserveWhen a request is accepted, Hermes reserves credits for the estimated prompt plus max_tokens of output (8,192 when you set none). Set max_tokens to keep the reservation small.
  2. SettleWhen the response finishes, the reservation is replaced by the exact charge from the usage the model reports: prompt tokens at the input rate, cached prompt tokens at the cache-read rate, completion tokens at the output rate. The remainder is released immediately.
  3. FailuresIf the model rejects the request nothing is charged. If a stream is interrupted after tokens were generated, the generated text is estimated and charged.

DeepSeek V4 Flash でできること

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-flash with a 1,048,576-token context. Vision is not listed for this specific Hermes entry. Check its current status, request capabilities and token price before use.

ユースケース

  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.

コードから DeepSeek V4 Flash を呼び出す

Any OpenAI SDK works: set the base URL and your Hermes key.

  1. 1

    API キーを作成

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

    Point your SDK at Hermes

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

    Send a chat completion

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

コード例

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-flash",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "max_tokens": 200
  }'

Request

POST https://api.hermes-ai.net/api/v1/chat/completions API key with the chat:create scope, or your signed-in session.

フィールド型備考
modelstringdeepseek/deepseek-v4-flash
messagesarrayOpenAI chat messages: system, user, assistant and tool roles; text and image_url parts.
streambooleanServer-sent events with a final usage chunk.
max_tokensintegerOutput cap; also sizes the credit reservation.
tools / tool_choicearray / objectFunction tools only.
response_formatobjectJSON mode and JSON schema where the model supports it.
temperature, top_p, stop, seed, reasoning_effortPassed through unchanged.

レスポンス

フィールド備考
choices[].message / deltaThe OpenAI chat completion shape.
usageprompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model.
hermes.charged_microsExact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests.
x-hermes-requestRequest id header, also used in the billing ledger.
error.codeDocumented Hermes error code; branch on it, not on the message.

DeepSeek V4 Flash API のよくある質問

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 Flash API on Hermes AI?

DeepSeek V4 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-flash.

What is the context window of DeepSeek V4 Flash?

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

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

Supported: ツール および JSON. Not supported: Vision, Reasoning および オーディオ. Streaming works with stream: true.

How is DeepSeek V4 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 Flash?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send deepseek/deepseek-v4-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 Flash?

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