Groq<\/a> provides ultra-fast inference on open-source models Get an API key from console.groq.com\/keys<\/a>.<\/p>\n<\/li>\n Set the API key:<\/p>\n<\/li>\n<\/ol>\n “`bash theme={“theme”:{“light”:”min-light”,”dark”:”min-dark”}} “`json5 theme={“theme”:{“light”:”min-light”,”dark”:”min-dark”}} If the Gateway runs as a daemon (launchd\/systemd), make sure Groq’s model catalog changes frequently. Run Popular choices include:<\/p>\n Groq Groq provides ultra-fast inference on open-source […]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[],"class_list":["post-627","post","type-post","status-publish","format-standard","hentry","category-docs"],"_links":{"self":[{"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/posts\/627","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/comments?post=627"}],"version-history":[{"count":2,"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/posts\/627\/revisions"}],"predecessor-version":[{"id":717,"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/posts\/627\/revisions\/717"}],"wp:attachment":[{"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/media?parent=627"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/categories?post=627"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pa.yingzhi8.cn\/index.php\/wp-json\/wp\/v2\/tags?post=627"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n(Llama, Gemma, Mistral, and more) using custom LPU hardware. OpenClaw connects
\nto Groq through its OpenAI-compatible API.<\/p>\n\n
groq<\/code><\/li>\nGROQ_API_KEY<\/code><\/li>\nQuick start<\/h2>\n
\n
\nexport GROQ_API_KEY=”gsk_…”<\/p>\n\n3. Set a default model:\n\n```json5 theme={"theme":{"light":"min-light","dark":"min-dark"}}\n{\n agents: {\n defaults: {\n model: { primary: "groq\/llama-3.3-70b-versatile" },\n },\n },\n}\n<\/code><\/pre>\nConfig file example<\/h2>\n
\n{
\n env: { GROQ_API_KEY: “gsk_…” },
\n agents: {
\n defaults: {
\n model: { primary: “groq\/llama-3.3-70b-versatile” },
\n },
\n },
\n}<\/p>\n\n## Audio transcription\n\nGroq also provides fast Whisper-based audio transcription. When configured as a\nmedia-understanding provider, OpenClaw uses Groq's `whisper-large-v3-turbo`\nmodel to transcribe voice messages.\n\n```json5 theme={"theme":{"light":"min-light","dark":"min-dark"}}\n{\n media: {\n understanding: {\n audio: {\n models: [{ provider: "groq" }],\n },\n },\n },\n}\n<\/code><\/pre>\nEnvironment note<\/h2>\n
GROQ_API_KEY<\/code> is
\navailable to that process (for example, in ~\/.openclaw\/.env<\/code> or via
\nenv.shellEnv<\/code>).<\/p>\nAvailable models<\/h2>\n
openclaw models list | grep groq<\/code>
\nto see currently available models, or check
\nconsole.groq.com\/docs\/models<\/a>.<\/p>\n\n
Links<\/h2>\n
\n