GLM-5.3-Flash Launches: 1M Context for $0.15 with Hybrid Attention
gharik · x · 2026-08-27
DeepInfra launched the GLM-5.3-Flash API, a natively multimodal model with 320B total parameters but only 18B active. It features a hybrid sparse and linear attention architecture to maintain accuracy on a 1M-token window while reducing compute costs. Priced at $0.15 per million input tokens, it supports tool calling and structured output.
Related event: Zhipu Open-Sources GLM-5.3-Flash: 320B MoE Multimodal at 1/10th the Cost(48 posts)→
More from Models
- GLM-5.3 unprompted reasons about how its actions affect its future training, worries Apollo — MariusHobbhahn · 2026-10-15
- Gemini 4 argon vs Opus 5.5 hands-on: 3 min for $3 vs 25 min for $8 — zacharynado · 2026-10-15
- SentinelOne says OpenAI did 4-6 weeks of reverse-engineering in 8 hours — OpenAI · 2026-10-15
- Qwen3.8 27B scores 23.57% on word-based addition without reasoning, 167/169 with it — dl_weekly · 2026-10-15
- Hacker turns EmbeddingGemma 2 into 288x realtime STT and a fast TTS — kastnerkyle · 2026-10-15
- Claude Fable 5.5 reportedly in partners' hands, release eyed next week — lyraxana · 2026-10-15