DeepSeek V4 on Cloudflare Workers AI: First 1M Token Context Models
ritakozlov · x · 2026-08-15
Cloudflare Workers AI has launched DeepSeek V4 Flash and Pro models. They are the first on the platform to feature a full 1 million token (1,048,576 tokens) context window, designed for long-horizon agentic workflows, large codebases, and multi-step reasoning.
Key capabilities:
- Reasoning: Both support a thinking mode for complex, step-by-step problem-solving.
- Function calling: Enables agents to invoke tools and APIs across multiple conversation turns.
- Long context: Full support for a 1 million token context window.
The V4 Flash variant is faster and more cost-effective, with substantially enhanced agentic capabilities over the preview version. Access requires a Workers Paid plan or prepaid AI Gateway credits.
Related event: DeepSeek V4 Series Debuts on Multiple Platforms with 1M Context(6 posts)→
More from Infra
- CoreWeave's debt costs falling: DDTL spreads tightened from S+9.62% to S+2.25% — BenBajarin · 2026-10-16
- SoftBank lines up US IPOs for SB Energy and AI robotics spinoff Roze, valuations top $50B — nordicinst · 2026-10-16
- TRL reproduces Modal's mixed-precision async RL: plain GRPO collapses, SC+MIS holds 0.72 — QGallouedec · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16