{"slug": "kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway", "title": "Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway", "summary": "Moonshot AI's Kimi K3 and Kimi K3 Fast models are now available on Vercel's AI Gateway from US-based providers including Baseten and Fireworks, with Zero Data Retention (ZDR) support. The models run on US infrastructure for data residency compliance, and AI Gateway automatically routes across providers for failover and higher uptime. Kimi K3 Fast costs ~50% more per token for lower latency, and regional pricing for US-only inference is ~10% higher.", "body_md": "[Kimi K3 from Moonshot AI](https://vercel.com/ai-gateway/models/kimi-k3) and its faster serving path, [Kimi K3 Fast](https://vercel.com/ai-gateway/models/kimi-k3-fast), are now available from US-based providers on AI Gateway, including Baseten and Fireworks. [Zero Data Retention](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) (ZDR) is also supported for both models.\n\nAs of 8:20 AM PDT, Fireworks is available. Baseten and other providers will be online shortly.\n\nRunning Kimi K3 on US-based providers lets teams with data residency and compliance requirements use the model on US infrastructure. Because AI Gateway serves the models from multiple providers, it automatically routes across them for failover, higher uptime, and more available throughput than any single provider offers. You call the same `moonshotai/kimi-k3`\n\nmodel ID, and the gateway handles provider selection and fallback.\n\nKimi K3 Fast trades a higher per-token cost for lower latency. Request it with the `speed`\n\noption on the base model, which stays on `moonshotai/kimi-k3`\n\nand falls back to standard speed when the fast tier is unavailable. Alternatively, use `moonshotai/kimi-k3-fast`\n\n. The fast variant costs ~50% more than the base model.\n\nTo use Kimi K3, set `model`\n\nto `moonshotai/kimi-k3`\n\nin the [AI SDK](https://ai-sdk.dev/):\n\nTo route Kimi K3 requests to use only US data centers for inference, set `inferenceRegion`\n\n. Regional pricing is ~10% more than the regular variant.\n\nZero Data Retention for Kimi K3 is also available. Turn on Zero Data Retention for every request from the [AI Gateway dashboard settings](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr), or set it per request with `zeroDataRetention`\n\n:\n\nTo see every provider serving Kimi K3, along with per-provider pricing, supported parameters, uptime, throughput, and latency, call the model endpoints API:\n\nModel prices vary by provider and variant type.\n\nRun `vercel ai-gateway coding-agents setup`\n\nand select Kimi K3. This will detect the agents on your machine, provision an AI Gateway key, and write their config. See how to set it up via the [Vercel CLI](https://vercel.com/docs/cli/ai-gateway#coding-agents).\n\nTry Kimi K3 in the [model playground](https://vercel.com/ai-gateway/models/kimi-k3).", "url": "https://wpnews.pro/news/kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/kimi-k3-and-kimi-k3-fast-on-ai-gateway", "published_at": "2026-07-27 00:00:00+00:00", "updated_at": "2026-07-27 15:38:57.456290+00:00", "lang": "en", "topics": ["ai-products", "ai-infrastructure", "ai-tools"], "entities": ["Moonshot AI", "Kimi K3", "Kimi K3 Fast", "Vercel", "AI Gateway", "Baseten", "Fireworks", "Zero Data Retention"], "alternates": {"html": "https://wpnews.pro/news/kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway", "markdown": "https://wpnews.pro/news/kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway.md", "text": "https://wpnews.pro/news/kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/kimi-k3-and-kimi-k3-fast-with-zdr-and-us-based-providers-now-on-ai-gateway.jsonld"}}