From 1e191ba81598291d51eef9df3219388938f26754 Mon Sep 17 00:00:00 2001 From: Jack Date: Mon, 27 Apr 2026 13:06:51 +0800 Subject: update Go DeepSeek request estimates for cache pricing changes (#24575) --- packages/web/src/content/docs/nb/go.mdx | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'packages/web/src/content/docs/nb') diff --git a/packages/web/src/content/docs/nb/go.mdx b/packages/web/src/content/docs/nb/go.mdx index 9caf39990..937362d1a 100644 --- a/packages/web/src/content/docs/nb/go.mdx +++ b/packages/web/src/content/docs/nb/go.mdx @@ -108,17 +108,18 @@ Tabellen nedenfor gir et estimert antall forespørsler basert på typiske bruksm | MiniMax M2.5 | 6,300 | 15,900 | 31,800 | | Qwen3.6 Plus | 3,300 | 8,200 | 16,300 | | Qwen3.5 Plus | 10,200 | 25,200 | 50,500 | -| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 | -| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 | +| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 | +| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 | Estimatene er basert på observerte gjennomsnittlige forespørselsmønstre: - GLM-5/5.1 — 700 input, 52 000 bufret, 150 output-tokens per forespørsel - Kimi K2.5/K2.6 — 870 input, 55 000 bufret, 200 output-tokens per forespørsel -- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request +- DeepSeek V4 Pro — 750 input, 82 000 bufret, 290 output-tokens per forespørsel +- DeepSeek V4 Flash — 790 input, 68 000 bufret, 280 output-tokens per forespørsel - MiniMax M2.7/M2.5 — 300 input, 55 000 bufret, 125 output-tokens per forespørsel -- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request -- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request +- Qwen3.5 Plus — 410 input, 47 000 bufret, 140 output-tokens per forespørsel +- Qwen3.6 Plus — 500 input, 57 000 bufret, 190 output-tokens per forespørsel - MiMo-V2-Pro — 350 input, 41 000 bufret, 250 output-tokens per forespørsel - MiMo-V2-Omni — 1000 input, 60 000 bufret, 140 output-tokens per forespørsel - MiMo-V2.5-Pro — 350 input, 41 000 bufret, 250 output-tokens per forespørsel -- cgit v1.2.3