explaingit

aldegad/tenstorrent

★ 15Audience · developerComplexity · 2/5ActiveLicenseSetup · easy

TLDR

A skill file that teaches AI coding assistants like Claude Code and Codex how to call Tenstorrent's hosted chat and text-to-video APIs.

Mindmap

mindmap
  root((tenstorrent))
    Inputs
      SKILL.md
      TENSTORRENT_KEY
      Prompts
    Outputs
      Chat replies
      Video jobs
    Use Cases
      Wire Claude Code to Tenstorrent
      Call DeepSeek-R1
      Submit Wan 2.2 video jobs
    Tech Stack
      Bash
      curl
      jq

Things people build with this

USE CASE 1

Wire Claude Code to call Tenstorrent hosted models

USE CASE 2

Run DeepSeek-R1 or Qwen3-32B chat calls from the terminal

USE CASE 3

Submit Wan 2.2 text-to-video jobs over HTTP

Tech stack

Bashcurljq

Getting it running

Difficulty · easy Time to first run · 5min

You need a Tenstorrent API key exported as TENSTORRENT_KEY before any of the curl examples will run.

MIT, do what you want, keep the copyright notice.

In plain English

This repository, aldegad/tenstorrent, is a small skill that teaches AI coding assistants such as Claude Code, OpenAI's Codex, and projects built on the Agent SDK how to talk to Tenstorrent's hosted API at console.tenstorrent.com. A skill in this context is a short instruction file plus a handful of examples that the assistant loads to learn a new external service. The Tenstorrent Console hosts two things the skill targets. The first is an OpenAI-compatible chat endpoint that serves a few open-weight models, including DeepSeek-R1, Qwen3-32B, and the multi-modal Qwen3-VL. The second is a text-to-video endpoint running Wan 2.2, where you submit a prompt and get back a video job. To install the skill, the README asks the user to drop the SKILL.md file into one of two known skill folders, either ~/.claude/skills/tenstorrent or ~/.codex/skills/tenstorrent. Once it is there, the matching assistant picks it up and follows the instructions inside. Authentication is one environment variable, TENSTORRENT_KEY, holding an API key generated from the Tenstorrent console. The README is explicit about not committing .env files or real keys. The two curl examples show the actual HTTP shape the skill teaches: a POST to /v1/chat/completions with a model name, messages array, and max_tokens for chat, and a POST to /v1/video/jobs with model Wan2.2-T2V-A14B-Diffusers, a prompt, and an optional negative_prompt for video. The chat example also extracts the reply with jq. The repository is small. There is a SKILL.md, a folder called examples that holds runnable versions of the commands above, a LICENSE file, and the MIT license is stated in the README. There is no build step, no runtime of its own, and no dependencies beyond curl and jq for the examples.

Copy-paste prompts

Prompt 1
Install SKILL.md from this repo into ~/.claude/skills/tenstorrent and confirm Claude Code can call DeepSeek-R1 with my TENSTORRENT_KEY
Prompt 2
Write a curl POST to /v1/chat/completions using Qwen3-32B and extract just the reply text with jq
Prompt 3
Submit a short text-to-video job to /v1/video/jobs using model Wan2.2-T2V-A14B-Diffusers and poll until the video URL is ready
Prompt 4
Copy the skill into ~/.codex/skills/tenstorrent and try a multi-modal Qwen3-VL request that includes an image
Open on GitHub → Explain another repo

Generated 2026-05-22 · Model: sonnet-4-6 · Verify against the repo before relying on details.