{"slug": "glm-5-2-is-now-available-on-telnyx-inference", "title": "GLM-5.2 is now available on Telnyx Inference", "summary": "Telnyx has added Z.ai's GLM-5.2 open-weight model to its Inference platform, hosted on owned B300 GPUs. The model leads Artificial Analysis with an Intelligence Index of 51, outperforming competitors, and uses Dynamic Sparse Attention to reduce FLOPs by 2.9x at long contexts. Telnyx claims customers switching from closed-source APIs see 75%+ cost reductions.", "body_md": "[Contact us](https://telnyx.com/contact-us)\n\n[Log in](https://portal.telnyx.com)\n\nGLM-5.2 by Z.ai is now available on [Telnyx Inference](https://telnyx.com/products/inference), hosted on our owned GPU infrastructure.\n\nGLM-5.2 is the [highest-ranked open-weight model on Artificial Analysis](https://artificialanalysis.ai/models/glm-5-2), with an Intelligence Index of 51, outpacing MiniMax-M3 (44), DeepSeek V4 Pro (44), and Kimi K2.6 (43). The model scores [99.2 on AIME 2026](https://artificialanalysis.ai/models/glm-5-2) and [62.1 on SWE-bench Pro](https://www.swebench.com/), placing it in the top tier for both reasoning and coding.\n\nThe model uses Dynamic Sparse Attention (DSA) with IndexShare, which reuses sparse attention indexers across every four transformer layers to reduce per-token FLOPs by 2.9x at 1M context. The result is stable long-context performance for codebase analysis, document processing, and multi-turn agent sessions, without the performance degradation that hits standard attention at long sequence lengths.\n\n`reasoning_effort`\n\nsettings, from faster responses to maximum depth on complex reasoning tasks.Telnyx owns the B300 GPUs running GLM-5.2, which means no cloud provider markup baked into every token, no rate limits set by a third party, and no rented GPU fleet introducing variable performance. We control the hardware and the network end to end, so throughput and latency are predictable, not best-effort.\n\nOpen-weight models are matching or beating closed-source on quality. The difference is price. Customers switching from closed-source APIs are seeing [75%+ cost reductions](https://telnyx.com/pricing/inference-api) with no compromise on quality and no vendor lock-in.\n\nSend your first request through the OpenAI-compatible Telnyx Inference API:\n\n```\ncurl https://api.telnyx.com/v2/ai/chat/completions \\\n  -H \"Authorization: Bearer $TELNYX_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"zai-org/GLM-5.2-FP8\",\n    \"messages\": [\n      {\"role\": \"user\", \"content\": \"Explain the IndexShare optimization in GLM-5.2.\"}\n    ]\n  }'\n```\n\n**Get started** with [Inference documentation](https://developers.telnyx.com/docs/inference/models) or [sign up](https://telnyx.com/sign-up) in the portal.", "url": "https://wpnews.pro/news/glm-5-2-is-now-available-on-telnyx-inference", "canonical_source": "https://telnyx.com/release-notes/glm-5-2-inference", "published_at": "2026-06-23 12:00:00+00:00", "updated_at": "2026-07-01 12:06:30.544865+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "ai-products", "ai-research"], "entities": ["Telnyx", "Z.ai", "GLM-5.2", "B300 GPU", "Artificial Analysis", "MiniMax-M3", "DeepSeek V4 Pro", "Kimi K2.6"], "alternates": {"html": "https://wpnews.pro/news/glm-5-2-is-now-available-on-telnyx-inference", "markdown": "https://wpnews.pro/news/glm-5-2-is-now-available-on-telnyx-inference.md", "text": "https://wpnews.pro/news/glm-5-2-is-now-available-on-telnyx-inference.txt", "jsonld": "https://wpnews.pro/news/glm-5-2-is-now-available-on-telnyx-inference.jsonld"}}