Aller au contenu

MoonshotLLM

Kimi K3.1 Pro API

Model IDmoonshotai/kimi-k3.1-pro

Kimi K3.1 Pro for long-horizon coding and research workflows.

  • 1.05M context
  • Outils
  • Vision
  • Reasoning

Lancez Kimi K3.1 Pro dans le playground

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

Paramètres

Modèle
model
moonshotai/kimi-k3.1-pro
messages[].content
messages[0].content
max_tokens
temperature

Aperçu de la requête

{"model": "moonshotai/kimi-k3.1-pro","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 Kimi K3.1 Pro with your account.

Usage and charge appear here after a reply.

Tarifs de Kimi K3.1 Pro

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 Kimi K3.1 Pro sait faire

Moonshot positions Kimi K3.1 Pro for long-horizon coding, research and complex agentic work. Its consumer product's agents and hosted creation tools are separate from the Hermes chat endpoint.

Hermes lists moonshotai/kimi-k3.1-pro with a 1,048,576-token context, tools, vision, reasoning and streaming; structured outputs are not listed. Check the current status and token rates before submitting a request.

Cas d’usage

  1. Analyze code and long documents

    Reserve context space for the response and supporting instructions.

  2. Use application-controlled tools

    Process tool calls and validate the results in your software.

  3. Review visual information

    Combine supported image input with written instructions.

Appelez Kimi K3.1 Pro 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 moonshotai/kimi-k3.1-pro

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": "moonshotai/kimi-k3.1-pro",
    "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
modelstringmoonshotai/kimi-k3.1-pro
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 Kimi K3.1 Pro

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

Are Moonshot's hosted creation tools included?

Not automatically. Moonshot's product and the Hermes chat route expose different interfaces and may offer different controls.

What is the Kimi K3.1 Pro API on Hermes AI?

Kimi K3.1 Pro by Moonshot is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID moonshotai/kimi-k3.1-pro.

What is the context window of Kimi K3.1 Pro?

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

Does Kimi K3.1 Pro 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 Kimi K3.1 Pro 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 Kimi K3.1 Pro?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send moonshotai/kimi-k3.1-pro 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 Kimi K3.1 Pro?

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