Saltar al contenido

QwenLLM

Qwen3.8 Flash Next API

Model IDqwen/qwen3.8-flash-next

Qwen3.8 Flash Next through the Hermes chat catalog.

  • 262K context
  • Herramientas
  • Vision
  • Reasoning
  • JSON

Ejecuta Qwen3.8 Flash Next en el playground

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

Parámetros

Modelo
model
qwen/qwen3.8-flash-next
messages[].content
messages[0].content
max_tokens
temperature

Vista previa de la solicitud

{"model": "qwen/qwen3.8-flash-next","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 Qwen3.8 Flash Next with your account.

Usage and charge appear here after a reply.

Precios de Qwen3.8 Flash Next

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 Qwen3.8 Flash Next

The Qwen team describes Flash Next as a cost-efficient foundation model for practical AI workflows. See the Qwen or Alibaba documentation for the native model. Manufacturer-hosted tools, multimodal inputs and product integrations do not automatically establish behavior on the Hermes route.

Hermes lists qwen/qwen3.8-flash-next with a 262,144-token context. Vision is listed for this channel. Check its current capability flags, availability and token price before use; the manufacturer and Hermes may list different limits.

Casos de uso

  1. Analyze text or code

    Evaluate results on representative tasks within the listed context.

  2. Build a tool workflow

    Use the supported Hermes request fields and validate tool results.

  3. Compare model choices

    Measure quality, latency and cost for the workload you intend to run.

Llama a Qwen3.8 Flash Next 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 qwen/qwen3.8-flash-next

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": "qwen/qwen3.8-flash-next",
    "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
modelstringqwen/qwen3.8-flash-next
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 Qwen3.8 Flash Next

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

Does the native model's multimodal support guarantee Hermes image or video input?

No. The manufacturer describes its platform; the exact Hermes channel's capability flags and API documentation define its supported inputs.

What is the Qwen3.8 Flash Next API on Hermes AI?

Qwen3.8 Flash Next by Qwen is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID qwen/qwen3.8-flash-next.

What is the context window of Qwen3.8 Flash Next?

262,144 tokens, shared by the prompt and the output.

Does Qwen3.8 Flash Next support vision, tools and JSON output?

Supported: Herramientas, Vision, Reasoning y JSON. Not supported: Audio. Streaming works with stream: true.

How is Qwen3.8 Flash Next 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 Qwen3.8 Flash Next?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send qwen/qwen3.8-flash-next 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 Qwen3.8 Flash Next?

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