{"slug": "gemini-3-5-flash-on-ai-gateway", "title": "Gemini 3.5 Flash on AI Gateway", "summary": "Vercel has added Gemini 3.5 Flash to its AI Gateway, offering developers access to the model with improved coding proficiency, reasoning, and multi-turn coherence. The model defaults to a medium thinking level to balance response quality with cost-efficient generation, though it does not support temperature, topP, topK, or thinking_budget parameters. AI Gateway provides a unified API for model calls, usage tracking, and performance optimizations, including custom reporting and intelligent provider routing.", "body_md": "Gemini 3.5 Flash is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway).\n\nThis model has improved coding proficiency and parallel agentic execution loops versus previous Flash versions. It also brings improvements to core reasoning, instruction following, and multi-turn coherence, with stronger performance on complex tasks and higher-quality reasoning traces in thinking mode.\n\n3.5 Flash defaults to the `medium`\n\nthinking level, balancing response quality with faster, more cost-efficient generation.\n\nTo use Gemini 3.5 Flash, set model to `google/gemini-3.5-flash`\n\nin the [AI SDK](https://ai-sdk.dev/).\n\nNote that `temperature`\n\n, `topP`\n\n, `topK`\n\n, and `thinking_budget`\n\nare not supported by this model.\n\nAI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in [custom reporting](https://vercel.com/docs/ai-gateway/capabilities/custom-reporting), [observability](https://vercel.com/docs/observability/ai-sdk-observability), [Bring Your Own Key](https://vercel.com/docs/ai-gateway#bring-your-own-key) support, and intelligent provider routing with automatic retries.\n\nLearn more about [AI Gateway](https://vercel.com/docs/ai-gateway), view the [AI Gateway model leaderboard](https://vercel.com/ai-gateway/leaderboards) or try it in our [model playground](https://vercel.com/ai-gateway/models/gemini-3.5-flash).", "url": "https://wpnews.pro/news/gemini-3-5-flash-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/gemini-3-5-flash-on-ai-gateway", "published_at": "2026-05-19 07:00:00+00:00", "updated_at": "2026-05-25 00:26:16.015492+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "ai-tools", "ai-infrastructure", "generative-ai"], "entities": ["Gemini 3.5 Flash", "Vercel AI Gateway", "AI SDK", "Google"], "alternates": {"html": "https://wpnews.pro/news/gemini-3-5-flash-on-ai-gateway", "markdown": "https://wpnews.pro/news/gemini-3-5-flash-on-ai-gateway.md", "text": "https://wpnews.pro/news/gemini-3-5-flash-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/gemini-3-5-flash-on-ai-gateway.jsonld"}}