{"slug": "gpt-6-2-astra-and-sol-now-available-on-ai-gateway", "title": "GPT-6.2 Astra and Sol now available on AI Gateway", "summary": "OpenAI's GPT-6.2 Astra and GPT-6.2 Sol are now available on Vercel's AI Gateway under the model IDs openai/gpt-6.2-astra and openai/gpt-6.2-sol, Vercel announced. GPT-6.2 Astra targets complex, multi-step projects with improvements to implementing and testing changes in existing codebases, following document templates, and computer use, while GPT-6.2 Sol covers everyday coding, writing, and agent workflows including building interactive web applications from a written brief. Both models support the Responses API and a fast mode plus OpenAI's Ultrafast service tier, and GPT-6.2 Astra's Ultrafast output-token price is 60% lower than GPT-6 Astra's.", "body_md": "[GPT-6.2 Astra](https://vercel.com/ai-gateway/models/gpt-6.2-astra) and [GPT-6.2 Sol](https://vercel.com/ai-gateway/models/gpt-6.2-sol) from [OpenAI](https://vercel.com/ai-gateway/models/providers/openai) are now available on [AI Gateway](https://vercel.com/ai-gateway).\n\n**GPT-6.2 Astra:** for complex, multi-step projects, with improvements to implementing and testing changes in existing codebases, following document templates, and computer use\n\n**GPT-6.2 Sol:** for everyday coding, writing, and agent workflows, including building interactive web applications from a written brief\n\nUse `openai/gpt-6.2-astra` or `openai/gpt-6.2-sol` as the model ID. For the API examples, set `AI_GATEWAY_API_KEY` to your [AI Gateway API key](https://vercel.com/docs/ai-gateway/authentication-and-byok/api-keys).\n\nBoth models also support the [Responses API](https://vercel.com/docs/ai-gateway/sdks-and-apis/responses).\n\nFor lower latency at higher per-token rates, both models support [fast mode](https://vercel.com/docs/ai-gateway/models-and-providers/fast-mode) and OpenAI’s [Ultrafast service tier](https://vercel.com/docs/ai-gateway/models-and-providers/service-tiers#ultrafast). To request Ultrafast, set `providerOptions.openai.serviceTier` to `'ultrafast'` in the AI SDK, or set `service_tier` to `'ultrafast'` in Chat Completions and Responses requests.\n\nGPT-6.2 Astra’s Ultrafast output-token price is 60% lower than GPT-6 Astra’s.\n\nTo use the models in coding agents like Codex, Cursor, and more, install the latest Vercel CLI and run setup:\n\nThen select `openai/gpt-6.2-astra` or `openai/gpt-6.2-sol` in the agent. See the [coding agents guide](https://vercel.com/docs/ai-gateway/coding-agents) for details.\n\nTry [GPT-6.2 Astra](https://vercel.com/ai-gateway/models/gpt-6.2-astra) or [GPT-6.2 Sol](https://vercel.com/ai-gateway/models/gpt-6.2-sol) in the playground.", "url": "https://wpnews.pro/news/gpt-6-2-astra-and-sol-now-available-on-ai-gateway", "canonical_source": "https://vercel.com/changelog/gpt-6-2-astra-and-sol-now-available-on-ai-gateway", "published_at": "2026-11-17 00:00:00+00:00", "updated_at": "2026-11-17 20:33:08.973324+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "ai-agents", "developer-tools", "ai-tools"], "entities": ["OpenAI", "Vercel", "AI Gateway", "GPT-6.2 Astra", "GPT-6.2 Sol", "Responses API", "Codex", "Cursor"], "also_reported_by": [], "takeaway": "Developers can call openai/gpt-6.2-astra or openai/gpt-6.2-sol through AI Gateway, and requesting OpenAI's Ultrafast tier via providerOptions.openai.serviceTier = 'ultrafast' gives GPT-6.2 Astra an output-token price 60% lower than GPT-6 Astra's.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/gpt-6-2-astra-and-sol-now-available-on-ai-gateway", "markdown": "https://wpnews.pro/news/gpt-6-2-astra-and-sol-now-available-on-ai-gateway.md", "text": "https://wpnews.pro/news/gpt-6-2-astra-and-sol-now-available-on-ai-gateway.txt", "jsonld": "https://wpnews.pro/news/gpt-6-2-astra-and-sol-now-available-on-ai-gateway.jsonld"}}