Providers

Telnyx

Telnyx AI inference provides hosted, OpenAI-compatible access to open-weight models plus proxied frontier routes. The vendor-maintained external @telnyx/openclaw-provider plugin supplies the runtime; OpenClaw carries its catalog and onboarding metadata. Authenticated discovery follows the complete model set enabled for your Telnyx account, while the offline fallback contains the models available when that plugin release was built.

Property	Value
Provider id	`telnyx`
Plugin	vendor-maintained external package (`@telnyx/openclaw-provider`)
Auth env var	`TELNYX_API_KEY`
Onboarding flag	`--auth-choice telnyx-api-key`
Direct CLI flag	`--telnyx-api-key <key>`
API	OpenAI-compatible (`openai-completions`)
Base URL	`https://api.telnyx.com/v2/ai/openai`
Default model	`telnyx/moonshotai/Kimi-K3`

Requirements

The catalog pin for @telnyx/openclaw-provider@0.2.0 requires OpenClaw 2026.8.1 or newer. Upgrade OpenClaw before installing the plugin:

bash

openclaw updateopenclaw --version

Install plugin

bash

openclaw plugins install telnyxopenclaw gateway restart

Getting started

Create a Telnyx account and API key

Create a key in the Telnyx API keys portal. Inference calls are usage-priced; see the Telnyx inference docs for current models and rates.

Run onboarding

Onboarding

openclaw onboard --auth-choice telnyx-api-key

Direct flag

openclaw onboard --non-interactive --accept-risk \  --auth-choice telnyx-api-key \  --telnyx-api-key "$TELNYX_API_KEY"

Env only

export TELNYX_API_KEY=...

In an interactive run, pick the Telnyx API key choice. For non-interactive setup, read the security guidance first; --accept-risk acknowledges that setup can write credentials and daemon configuration without prompting.

Verify the live catalog

bash

openclaw models list --refresh --provider telnyx

With usable auth, the plugin requests the authenticated /models endpoint and lists every model returned for the account. Without auth, it stays offline and uses the bundled fallback.

Default model

telnyx/moonshotai/Kimi-K3 is the default model. In OpenClaw it supports text and image input, tool calling, reasoning, a 1M-token context window, and up to 64k output tokens:

json5

{  agents: {    defaults: {      model: { primary: "telnyx/moonshotai/Kimi-K3" },    },  },}

Use /model telnyx/moonshotai/Kimi-K3 to switch an existing chat.

Live model discovery

The plugin fetches the authenticated /models endpoint and caches the result for five minutes, then merges those rows over the bundled catalog. Newly launched Telnyx models appear automatically without waiting for a plugin release, including proxied frontier routes such as telnyx/openai/gpt-5.x, telnyx/anthropic/claude-haiku-4-5, and telnyx/google/gemini-2.5-flash.

Bundled fallback catalog

The authenticated live catalog is authoritative. These rows keep setup and model selection useful before discovery succeeds:

Model ref	Input	Context	Max output
`telnyx/moonshotai/Kimi-K3`	text, image	1M	64k
`telnyx/moonshotai/Kimi-K2.6`	text, image	262k	8k
`telnyx/moonshotai/Kimi-K2.5`	text, image	256k	8k
`telnyx/zai-org/GLM-5.2`	text	1M	131k
`telnyx/zai-org/GLM-5.1-FP8`	text	202k	8k
`telnyx/MiniMaxAI/MiniMax-M3-MXFP8`	text	1M	8k
`telnyx/MiniMaxAI/MiniMax-M2.7`	text	200k	8k
`telnyx/Qwen/Qwen3-235B-A22B`	text	32k	8k
`telnyx/openai/gpt-5.4`	text	400k	8k
`telnyx/openai/gpt-5.4-mini`	text	400k	8k
`telnyx/openai/gpt-5.2`	text	400k	8k
`telnyx/openai/gpt-5.1`	text	400k	8k
`telnyx/openai/gpt-5`	text	400k	8k
`telnyx/anthropic/claude-haiku-4-5`	text	400k	8k

All bundled models support tool calling and reasoning. The openai/* and anthropic/* ids are Telnyx-proxied frontier routes; the rest are Telnyx-hosted open-weight models. Streaming usage is reported on the final chunk.

Manual config

Most setups only need the API key. To pin the provider explicitly:

json5

{  env: { vars: { TELNYX_API_KEY: "..." } },  agents: {    defaults: {      model: { primary: "telnyx/moonshotai/Kimi-K3" },    },  },  models: {    mode: "merge",    providers: {      telnyx: {        baseUrl: "https://api.telnyx.com/v2/ai/openai",        apiKey: "${TELNYX_API_KEY}",        api: "openai-completions",        models: [          {            id: "moonshotai/Kimi-K3",            name: "Kimi K3",            reasoning: true,            input: ["text", "image"],            contextWindow: 1000000,            maxTokens: 64000,          },        ],      },    },  },}

Model providers

Choosing providers, model refs, and failover behavior.

Thinking modes

Select OpenClaw reasoning effort levels.

Models CLI

List, inspect, and select discovered models.

Models FAQ

Auth profiles and model-selection troubleshooting.

Was this useful?