Skip to Content
Launching the open-source gateway

Provider: Tera

Call Tera models through Respan Gateway with unified logs, cost, and latency.

This page is for Respan LLM Gateway users.

Use Respan Gateway to call Tera models (tera/moonshotai/Kimi-K3) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Paste this into your coding agent:

Help me set up the Respan gateway to call Tera models. Follow https://www.respan.ai/docs/documentation/agent-setup.md

Quick setup

Get a Respan API key

Sign up  and create a key on the API keys page .

Send your first request

Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.

Tera is OpenAI-compatible. Point the OpenAI SDK at the Respan gateway and call any Tera model with the tera/ prefix.

from openai import OpenAI client = OpenAI( api_key="YOUR_RESPAN_API_KEY", base_url="https://api.respan.ai/api", ) response = client.chat.completions.create( model="tera/moonshotai/Kimi-K3", messages=[{"role": "user", "content": "Hello, Tera!"}], ) print(response.choices[0].message.content)

More integrations

Tera models work with every Respan gateway integration:

Switch models

Change the model parameter to call any supported model through the same client. Use the tera/ prefix to disambiguate when routing across providers. Browse the full list on the Models page .

client.chat.completions.create(model="tera/moonshotai/Kimi-K3", messages=messages) client.chat.completions.create(model="openai/gpt-6-sol", messages=messages) client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)

Use your own Tera key (BYOK)

Credits are the default path. If you’d rather bill Tera directly, attach your own provider key.

Open Providers

Go to the Providers page .

Add Tera

Select Tera and paste your tera.api_key.

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Tera key than the default.

{ "customer_credentials": { "tera": { "api_key": "YOUR_TERA_API_KEY" } }, "credential_override": { "tera/moonshotai/Kimi-K3": { "api_key": "ANOTHER_TERA_API_KEY" } } }

Log without proxying (Optional)

Already calling Tera directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

import requests requests.post( "https://api.respan.ai/api/request-logs/create/", headers={ "Authorization": "Bearer YOUR_RESPAN_API_KEY", "Content-Type": "application/json", }, json={ "model": "tera/moonshotai/Kimi-K3", "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}], "completion_message": {"role": "assistant", "content": "Hello from Tera through Respan."}, "cost": 0.001, "generation_time": 1.2, "customer_params": {"customer_identifier": "user_123"}, }, )

See the logging guide for the full setup.