Aller au contenu

ByteDanceLLM

Doubao Seed 2.1 Lite API

Model IDbytedance/doubao-seed-2.1-lite

Doubao Seed 2.1 Lite through the Hermes chat catalog.

  • 1.05M context
  • Outils
  • Vision
  • Reasoning

Lancez Doubao Seed 2.1 Lite dans le playground

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

Paramètres

Modèle
model
bytedance/doubao-seed-2.1-lite
messages[].content
messages[0].content
max_tokens
temperature

Aperçu de la requête

{"model": "bytedance/doubao-seed-2.1-lite","messages": [],"stream": true,"max_tokens": 1024}

Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.

Résultat

Send a message to run Doubao Seed 2.1 Lite with your account.

Usage and charge appear here after a reply.

Tarifs de Doubao Seed 2.1 Lite

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

Chargement du prix…
  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.

Ce que Doubao Seed 2.1 Lite sait faire

ByteDance describes the Seed 2.1 family as built for practical agent and productivity tasks. See ByteDance's Seed 2.1 announcement for the manufacturer’s description. Native product integrations and multimodal capabilities do not automatically establish what this Hermes route exposes.

The Hermes catalog lists bytedance/doubao-seed-2.1-lite with a 1,048,576-token context. Vision is listed and tools are listed for this entry. Check its current status and price before sending a request.

Cas d’usage

  1. Analyze text or code

    Evaluate the model on representative tasks within its listed context.

  2. Build an application workflow

    Use only request features listed for this channel and validate the result.

  3. Compare model options

    Test quality, latency and cost against the needs of your workload.

Appelez Doubao Seed 2.1 Lite depuis votre code

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

  1. 1

    Créez une clé d’API

    In the dashboard, with the chat:create scope. Clés d’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 bytedance/doubao-seed-2.1-lite

Exemples de code

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-2.1-lite",
    "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.

ChampTypeRemarques
modelstringbytedance/doubao-seed-2.1-lite
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.

Réponse

ChampRemarques
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.

FAQ de l’API Doubao Seed 2.1 Lite

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

Can I assume all native Seed features are available through Hermes?

No. ByteDance's description covers its own products; the selected Hermes entry's capability flags and API documentation define this channel's available features.

What is the Doubao Seed 2.1 Lite API on Hermes AI?

Doubao Seed 2.1 Lite 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-2.1-lite.

What is the context window of Doubao Seed 2.1 Lite?

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

Does Doubao Seed 2.1 Lite support vision, tools and JSON output?

Supported: Outils, Vision et la Reasoning. Not supported: JSON et la Audio. Streaming works with stream: true.

How is Doubao Seed 2.1 Lite 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 2.1 Lite?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send bytedance/doubao-seed-2.1-lite 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 2.1 Lite?

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