Saltar al contenido

DeepSeekLLM

DeepSeek V4 Flash API

Model IDdeepseek/deepseek-v4-flash

DeepSeek V4 Flash through the Hermes chat catalog.

  • 1.05M context
  • Herramientas
  • JSON

Ejecuta DeepSeek V4 Flash en el playground

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

Parámetros

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

Vista previa de la solicitud

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

El playground web envía este cuerpo con tu sesión iniciada. Desde código, envía el mismo cuerpo con una clave de API.

Resultado

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

Usage and charge appear here after a reply.

Precios de DeepSeek V4 Flash

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

Cargando precio…
  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.

Qué puede hacer DeepSeek V4 Flash

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.

Casos de uso

  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.

Llama a DeepSeek V4 Flash desde código

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

  1. 1

    Crea una clave de API

    In the dashboard, with the chat:create scope. Claves de API
  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

Ejemplos de código

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.

CampoTipoNotas
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.

Respuesta

CampoNotas
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.

Preguntas frecuentes sobre la API de DeepSeek V4 Flash

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: Herramientas y JSON. Not supported: Vision, Reasoning y Audio. 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 Claves de API in the dashboard with the chat:create scope, then add credits on the Billing page.