Skip to content

ByteDanceLLM

Doubao Seed Evolving API

Model IDbytedance/doubao-seed-evolving

Doubao Seed Evolving for agent and coding tasks.

  • 262K context
  • Tools
  • Vision
  • Reasoning

Run Doubao Seed Evolving in the playground

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

Parameters

Model
model
bytedance/doubao-seed-evolving
messages[].content
messages[0].content
max_tokens
temperature

Request preview

{"model": "bytedance/doubao-seed-evolving","messages": [],"stream": true,"max_tokens": 1024}

The web playground sends this body with your signed-in session. From code, send the same body with an API key.

Result

Send a message to run Doubao Seed Evolving with your account.

Usage and charge appear here after a reply.

Doubao Seed Evolving pricing

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

Loading price…
  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.

What Doubao Seed Evolving can do

Volcano Engine describes Seed Evolving as a dynamically updated model for agent and coding tasks. Its own API's model ID receives version updates; that policy does not establish identical behavior for a separate Hermes upstream route.

The Hermes catalog lists bytedance/doubao-seed-evolving with a 262,144-token context, tools, vision, reasoning and streaming. The manufacturer's documentation describes a larger native context in later updates; follow the Hermes channel's listed limit and check its status and price.

Use cases

  1. Develop code

    Analyze and modify code with appropriate review and validation.

  2. Build agent workflows

    Handle tool calls in your application and verify outcomes.

  3. Review supported images

    Combine image input with a text prompt.

Call Doubao Seed Evolving from code

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

  1. 1

    Create an API key

    In the dashboard, with the chat:create scope. API keys
  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 bytedance/doubao-seed-evolving

Code examples

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": "bytedance/doubao-seed-evolving",
    "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.

FieldTypeNotes
modelstringbytedance/doubao-seed-evolving
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.

Response

FieldNotes
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.

Doubao Seed Evolving API FAQ

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

Will Hermes always route to the newest Volcano Engine model version?

That is not established. Volcano Engine describes automatic updates for its own model ID; Hermes may use a different upstream mapping.

What is the Doubao Seed Evolving API on Hermes AI?

Doubao Seed Evolving by ByteDance is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID bytedance/doubao-seed-evolving.

What is the context window of Doubao Seed Evolving?

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

Does Doubao Seed Evolving support vision, tools and JSON output?

Supported: Tools, Vision and Reasoning. Not supported: JSON and Audio. Streaming works with stream: true.

How is Doubao Seed Evolving 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 Doubao Seed Evolving?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send bytedance/doubao-seed-evolving 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 Doubao Seed Evolving?

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