DeepSeek v4.1 flash provider shortage: Baseten slow, official API overloaded
shensi · x · 2026-11-04
A user praises mergeapi for shipping requested features within 24 hours multiple times, but complains there are too few providers for DeepSeek v4.1 flash (1017): Baseten has poor TPS, DeepSeek's official endpoint is sometimes overloaded and rejects requests, and Particle's caching is flaky — asking for more providers. The attached screenshot compares provider pricing for the 1M-context model, e.g. DeepInfra at $0.098/$0.294 per M tokens (55% off), Sail Research at $0.09/$0.30, Mistral at $0.30/$1.20.
More from Infra
- Satellite study constrains hyperscale data-centre heat footprint, contradicting earlier alarm — AndyMasley · 2026-11-05
- vLLM ships day-0 support for Kimi K3.1 across NVIDIA, AMD and TPUs — vllm_project · 2026-11-05
- vLLM + Megatron add Day-0 RL support and long-agent serving for Kimi K3.1 — vllm_project · 2026-11-05
- Kimi K3.1 Pro hits 61.2% on long-horizon code bench, up from 55.95% — vllm_project · 2026-11-05
- CoreWeave Shares Hit 52-Week Low as AI Compute Leasing Stocks Slip — GaryMarcus · 2026-11-05
- Ollama's free plan goes pay-as-you-go Nov 9: six cloud models will need credits — shoumikgoswami · 2026-11-05