{"slug": "ember-1-from-fireworks-now-available-on-ai-gateway", "title": "Ember-1 from Fireworks now available on AI Gateway", "summary": "Fireworks' Ember-1, a research preview reasoning model built on Kimi K3 for coding and agentic workflows, is now available on Vercel's AI Gateway under the model name fireworks/ember-1. Fireworks reports Ember-1 generates approximately 40% fewer tokens than Kimi K3 at comparable quality across its evaluations, and the model supports a 1M-token context window, text and image input, tool calling, and implicit prompt caching. The research preview has an initial two-week window, with the Fireworks endpoint supporting Zero Data Retention and No Prompt Training.", "body_md": "[Ember-1](https://vercel.com/ai-gateway/models/ember-1) from Fireworks is now available on [AI Gateway](https://vercel.com/ai-gateway).\n\nEmber-1 is a research preview reasoning model built on [Kimi K3](https://vercel.com/ai-gateway/models/kimi-k3) for coding and agentic workflows.\n\nFireworks reports approximately 40% fewer generated tokens than Kimi K3 at comparable quality across its evaluations. For coding agents that make repeated model calls, shorter reasoning traces can reduce output costs and the amount of context carried into later steps.\n\nEmber-1 supports a 1M-token context window, text and image input, tool calling, and [implicit prompt caching](https://vercel.com/docs/ai-gateway/models-and-providers/automatic-caching). The Fireworks endpoint supports [Zero Data Retention](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) and [No Prompt Training](https://vercel.com/docs/ai-gateway/security-and-compliance/disallow-prompt-training).\n\nThis model is available as a research preview with an initial two-week window.\n\nTo get started, use `fireworks/ember-1` for the model name across APIs and coding agents:\n\nTo use Ember-1 in your [coding agent](https://vercel.com/docs/ai-gateway/coding-agents), run the setup command with the [Vercel CLI](https://vercel.com/docs/cli/ai-gateway):\n\nThe command detects installed agents, provisions or reuses an AI Gateway API key, and configures their connection to the gateway. Then select `fireworks/ember-1` in your agent's model configuration.\n\nAI Gateway provides a unified API for calling models, with built-in [usage and cost tracking](https://vercel.com/docs/ai-gateway/observability-and-spend), [budgets for API keys](https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys), and [routing rules](https://vercel.com/docs/ai-gateway/models-and-providers/routing-rules).\n\nTry Ember-1 in the [model playground](https://vercel.com/ai-gateway/models/ember-1).", "url": "https://wpnews.pro/news/ember-1-from-fireworks-now-available-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/ember-1-from-fireworks-now-available-on-ai-gateway", "published_at": "2026-09-27 00:00:00+00:00", "updated_at": "2026-09-28 01:29:56.787453+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-tools", "developer-tools", "ai-infrastructure"], "entities": ["Fireworks", "Ember-1", "Kimi K3", "Vercel", "AI Gateway", "Vercel CLI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ember-1-from-fireworks-now-available-on-ai-gateway", "markdown": "https://wpnews.pro/news/ember-1-from-fireworks-now-available-on-ai-gateway.md", "text": "https://wpnews.pro/news/ember-1-from-fireworks-now-available-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/ember-1-from-fireworks-now-available-on-ai-gateway.jsonld"}}