Gateway Credits

The LLM Gateway is in beta.

Gateway Credits let you call LangChain-hosted models through the standard LLM Gateway API without setting up a provider account or key. Authenticate with only your LangSmith API key. No provider secret is required. The gateway routes each request based on its model ID. A hosted model slug such as moonshotai/kimi-k3 uses Gateway Credits. A model ID that starts with a configured bring-your-own-key provider, such as anthropic/claude-opus-5, uses that provider’s secret instead.

Gateway Credits are available on paid plans other than Enterprise.

Available models

Select a hosted model by ID in the request body. Model IDs are case-insensitive.

Model ID	Description
`moonshotai/kimi-k2.6`	Kimi K2.6 by Moonshot AI. A strong general-purpose model. Powered by Fireworks Inference.
`moonshotai/kimi-k3`	Kimi K3 by Moonshot AI. Powered by Fireworks Inference.

To list every model available to your workspace, including configured bring-your-own-key providers and hosted models, call GET /v1/models. Use a returned model ID exactly as shown in the model field of a prompt request.

Make a call

Hosted models use the same standard API formats as bring-your-own-key models. Point an OpenAI-compatible client at https://gateway.smith.langchain.com/v1, authenticate with your workspace-scoped LangSmith API key, and set model to a hosted model ID. For key types, permissions, and the header each client sends, see Authenticate to the LLM Gateway.

curl https://gateway.smith.langchain.com/v1/chat/completions \
    -H "Authorization: Bearer $LANGSMITH_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"model":"moonshotai/kimi-k3","messages":[{"role":"user","content":"ping"}]}'

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.smith.langchain.com/v1",
    api_key=os.environ["LANGSMITH_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/kimi-k3",
    messages=[{"role": "user", "content": "ping"}],
)
print(response.choices[0].message.content)

import os

from langchain.chat_models import init_chat_model

model = init_chat_model(
    model="moonshotai/kimi-k3",
    model_provider="openai",
    base_url="https://gateway.smith.langchain.com/v1",
    api_key=os.environ["LANGSMITH_API_KEY"],
)
print(model.invoke("ping").content)

This example calls the US gateway on LangSmith Cloud. For other regions, see Use a regional gateway.

Pricing

Gateway Credits are denominated in LangChain Standard Units (LSUs); each call consumes LSUs based on token usage. For plan details and current rates, see the pricing page. Standard gateway spend policies apply to hosted-model traffic, so any configured organization, workspace, API key, or user cap also governs Gateway Credit usage. You can control Gateway Credit consumption with the same tools you use for bring-your-own-key providers. For example, cap a specific API key at $200/month across every provider, or set a workspace-wide daily limit that includes hosted-model calls.

Tracing

Like all gateway traffic, hosted-model calls are traced to LangSmith. For where traces land and how to control access to them, see View LLM Gateway traces.

Next steps

Send your first LLM Gateway request: make your first gateway-proxied call.
API formats: call models through Chat Completions, Messages, or Responses.
Spend policies: add cost limits to Gateway Credit usage.
Direct model access: use provider-native APIs and model IDs.

Connect these docs to your agent of choice via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Get started

Call the gateway

Models and reliability

Authentication

Observability

Governance

Available models

Make a call

Pricing

Tracing

Next steps

​Available models

​Make a call

​Pricing

​Tracing

​Next steps

Available models

Make a call

Pricing

Tracing

Next steps