qwen3.8-omni-flash API — Hermes AI API

Conversation

Send a message to run qwen3.8-omni-flash with your account.

Settings

System promptmax_tokenstemperature

Last response

Usage and charge appear here after a reply.

About this model

qwen3.8-omni-flash is served through the Hermes AI OpenAI-compatible chat completions endpoint. Send the standard messages array; streaming, function tools, JSON output and reasoning settings pass through unchanged. You pay per token from prepaid credits, at the rates on the Pricing tab.

Property	Value
Model id	`qwen/qwen3.8-omni-flash`
Vendor	Qwen
Context window	1,000,000 tokens
Capabilities	Tools, Vision, Reasoning, Audio, Streaming
Endpoint	`https://api.hermes-ai.net/api/v1/chat/completions`
Hermes AI price	Loading price…

Request

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

Field	Type	Notes
model	string	`qwen/qwen3.8-omni-flash`
messages	array	OpenAI chat messages: system, user, assistant and tool roles; text and image_url parts.
stream	boolean	Server-sent events with a final usage chunk.
max_tokens	integer	Output cap; also sizes the credit reservation.
tools / tool_choice	array / object	Function tools only.
response_format	object	JSON mode and JSON schema where the model supports it.
temperature, top_p, stop, seed, reasoning_effort		Passed through unchanged.

Response

Field	Notes
choices[].message / delta	The OpenAI chat completion shape.
usage	prompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model.
hermes.charged_micros	Exact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests.
x-hermes-request	Request id header, also used in the billing ledger.
error.code	Documented Hermes error code; branch on it, not on the message.

Token prices

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

Loading price…

How token billing works

When 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.
When 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.
If the model rejects the request nothing is charged. If a stream is interrupted after tokens were generated, the generated text is estimated and charged.

Code examples

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

shell

export HERMES_API_KEY=your_api_key

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