Skip to content

Commit 1e191ba

Browse files
MrMushrooooomMrMushrooooom
authored
update Go DeepSeek request estimates for cache pricing changes (#24575)
1 parent f19d863 commit 1e191ba

19 files changed

Lines changed: 108 additions & 90 deletions

File tree

‎packages/console/app/src/routes/go/index.tsx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -65,10 +65,10 @@ function LimitsGraph(props: { href: string }) {
6565
{ id: "glm-5.1", name: "GLM-5.1", req: 880, d: "100ms" },
6666
{ id: "kimi-k2.6", name: "Kimi K2.6 (3x usage)", req: 3450, baseReq: 1150, d: "150ms" },
6767
{ id: "mimo-v2.5-pro", name: "MiMo-V2.5-Pro", req: 1290, d: "150ms" },
68-
{ id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", req: 1300, d: "200ms" },
68+
{ id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", req: 3450, d: "200ms" },
6969
{ id: "qwen3.6-plus", name: "Qwen3.6 Plus", req: 3300, d: "280ms" },
7070
{ id: "minimax-m2.7", name: "MiniMax M2.7", req: 3400, d: "300ms" },
71-
{ id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", req: 7450, d: "340ms" },
71+
{ id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", req: 5750, d: "340ms" },
7272
{ id: "qwen3.5-plus", name: "Qwen3.5 Plus", req: 10200, d: "360ms" },
7373
]
7474

‎packages/web/src/content/docs/ar/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -98,17 +98,18 @@ OpenCode Go حاليًا في المرحلة التجريبية.
9898
| MiniMax M2.7 | 3,400 | 8,500 | 17,000 |
9999
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
100100
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
101-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
102-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
101+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
102+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
103103

104104
تستند التقديرات إلى متوسطات أنماط الطلبات المرصودة:
105105

106106
- GLM-5/5.1 — ‏700 input، و52,000 cached، و150 output tokens لكل طلب
107107
- Kimi K2.5/K2.6 — ‏870 input، و55,000 cached، و200 output tokens لكل طلب
108-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
108+
- DeepSeek V4 Pro — ‏750 input، و82,000 cached، و290 output tokens لكل طلب
109+
- DeepSeek V4 Flash — ‏790 input، و68,000 cached، و280 output tokens لكل طلب
109110
- MiniMax M2.7/M2.5 — ‏300 input، و55,000 cached، و125 output tokens لكل طلب
110-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
111-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
111+
- Qwen3.5 Plus — ‏410 input، و47,000 cached، و140 output tokens لكل طلب
112+
- Qwen3.6 Plus — ‏500 input، و57,000 cached، و190 output tokens لكل طلب
112113
- MiMo-V2-Pro — ‏350 input، و41,000 cached، و250 output tokens لكل طلب
113114
- MiMo-V2-Omni — ‏1000 input، و60,000 cached، و140 output tokens لكل طلب
114115
- MiMo-V2.5-Pro — ‏350 input، و41,000 cached، و250 output tokens لكل طلب

‎packages/web/src/content/docs/bs/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -108,17 +108,18 @@ Tabela ispod pruža procijenjeni broj zahtjeva na osnovu tipičnih obrazaca kori
108108
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
109109
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
110110
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
111-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
112-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
111+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
112+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
113113

114114
Procjene se zasnivaju na zapaženim prosječnim obrascima zahtjeva:
115115

116116
- GLM-5/5.1 — 700 ulaznih (input), 52,000 keširanih, 150 izlaznih (output) tokena po zahtjevu
117117
- Kimi K2.5/K2.6 — 870 ulaznih, 55,000 keširanih, 200 izlaznih tokena po zahtjevu
118-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
118+
- DeepSeek V4 Pro — 750 ulaznih, 82,000 keširanih, 290 izlaznih tokena po zahtjevu
119+
- DeepSeek V4 Flash — 790 ulaznih, 68,000 keširanih, 280 izlaznih tokena po zahtjevu
119120
- MiniMax M2.7/M2.5 — 300 ulaznih, 55,000 keširanih, 125 izlaznih tokena po zahtjevu
120-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
121-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
121+
- Qwen3.5 Plus — 410 ulaznih, 47,000 keširanih, 140 izlaznih tokena po zahtjevu
122+
- Qwen3.6 Plus — 500 ulaznih, 57,000 keširanih, 190 izlaznih tokena po zahtjevu
122123
- MiMo-V2-Pro — 350 ulaznih, 41,000 keširanih, 250 izlaznih tokena po zahtjevu
123124
- MiMo-V2-Omni — 1000 ulaznih, 60,000 keširanih, 140 izlaznih tokena po zahtjevu
124125
- MiMo-V2.5-Pro — 350 ulaznih, 41,000 keširanih, 250 izlaznih tokena po zahtjevu

‎packages/web/src/content/docs/da/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -108,17 +108,18 @@ Tabellen nedenfor giver et estimeret antal anmodninger baseret på typiske Go-fo
108108
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
109109
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
110110
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
111-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
112-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
111+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
112+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
113113

114114
Estimaterne er baseret på observerede gennemsnitlige anmodningsmønstre:
115115

116116
- GLM-5/5.1 — 700 input, 52.000 cachelagrede, 150 output-tokens pr. anmodning
117117
- Kimi K2.5/K2.6 — 870 input, 55.000 cachelagrede, 200 output-tokens pr. anmodning
118-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
118+
- DeepSeek V4 Pro — 750 input, 82.000 cachelagrede, 290 output-tokens pr. anmodning
119+
- DeepSeek V4 Flash — 790 input, 68.000 cachelagrede, 280 output-tokens pr. anmodning
119120
- MiniMax M2.7/M2.5 — 300 input, 55.000 cachelagrede, 125 output-tokens pr. anmodning
120-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
121-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
121+
- Qwen3.5 Plus — 410 input, 47.000 cachelagrede, 140 output-tokens pr. anmodning
122+
- Qwen3.6 Plus — 500 input, 57.000 cachelagrede, 190 output-tokens pr. anmodning
122123
- MiMo-V2-Pro — 350 input, 41.000 cachelagrede, 250 output-tokens pr. anmodning
123124
- MiMo-V2-Omni — 1000 input, 60.000 cachelagrede, 140 output-tokens pr. anmodning
124125
- MiMo-V2.5-Pro — 350 input, 41.000 cachelagrede, 250 output-tokens pr. anmodning

‎packages/web/src/content/docs/de/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -100,17 +100,18 @@ Die folgende Tabelle zeigt eine geschätzte Anzahl von Anfragen basierend auf ty
100100
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
101101
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
102102
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
103-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
104-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
103+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
104+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
105105

106106
Die Schätzungen basieren auf beobachteten durchschnittlichen Anfragemustern:
107107

108108
- GLM-5/5.1 — 700 Input-, 52.000 Cached-, 150 Output-Tokens pro Anfrage
109109
- Kimi K2.5/K2.6 — 870 Input-, 55.000 Cached-, 200 Output-Tokens pro Anfrage
110-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
110+
- DeepSeek V4 Pro — 750 Input-, 82.000 Cached-, 290 Output-Tokens pro Anfrage
111+
- DeepSeek V4 Flash — 790 Input-, 68.000 Cached-, 280 Output-Tokens pro Anfrage
111112
- MiniMax M2.7/M2.5 — 300 Input-, 55.000 Cached-, 125 Output-Tokens pro Anfrage
112-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
113-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
113+
- Qwen3.5 Plus — 410 Input-, 47.000 Cached-, 140 Output-Tokens pro Anfrage
114+
- Qwen3.6 Plus — 500 Input-, 57.000 Cached-, 190 Output-Tokens pro Anfrage
114115
- MiMo-V2-Pro — 350 Input-, 41.000 Cached-, 250 Output-Tokens pro Anfrage
115116
- MiMo-V2-Omni — 1.000 Input-, 60.000 Cached-, 140 Output-Tokens pro Anfrage
116117
- MiMo-V2.5-Pro — 350 Input-, 41.000 Cached-, 250 Output-Tokens pro Anfrage

‎packages/web/src/content/docs/es/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -108,17 +108,18 @@ La siguiente tabla proporciona una cantidad estimada de peticiones basada en los
108108
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
109109
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
110110
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
111-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
112-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
111+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
112+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
113113

114114
Las estimaciones se basan en los patrones de peticiones promedio observados:
115115

116116
- GLM-5/5.1 — 700 tokens de entrada, 52,000 en caché, 150 tokens de salida por petición
117117
- Kimi K2.5/K2.6 — 870 tokens de entrada, 55,000 en caché, 200 tokens de salida por petición
118-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
118+
- DeepSeek V4 Pro — 750 tokens de entrada, 82,000 en caché, 290 tokens de salida por petición
119+
- DeepSeek V4 Flash — 790 tokens de entrada, 68,000 en caché, 280 tokens de salida por petición
119120
- MiniMax M2.7/M2.5 — 300 tokens de entrada, 55,000 en caché, 125 tokens de salida por petición
120-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
121-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
121+
- Qwen3.5 Plus — 410 tokens de entrada, 47,000 en caché, 140 tokens de salida por petición
122+
- Qwen3.6 Plus — 500 tokens de entrada, 57,000 en caché, 190 tokens de salida por petición
122123
- MiMo-V2-Pro — 350 tokens de entrada, 41,000 en caché, 250 tokens de salida por petición
123124
- MiMo-V2-Omni — 1000 tokens de entrada, 60,000 en caché, 140 tokens de salida por petición
124125
- MiMo-V2.5-Pro — 350 tokens de entrada, 41,000 en caché, 250 tokens de salida por petición

‎packages/web/src/content/docs/fr/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -98,17 +98,18 @@ Le tableau ci-dessous fournit une estimation du nombre de requêtes basée sur d
9898
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
9999
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
100100
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
101-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
102-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
101+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
102+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
103103

104104
Les estimations sont basées sur les modèles de requêtes moyens observés :
105105

106106
- GLM-5/5.1 — 700 tokens en entrée, 52,000 en cache, 150 tokens en sortie par requête
107107
- Kimi K2.5/K2.6 — 870 tokens en entrée, 55,000 en cache, 200 tokens en sortie par requête
108-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
108+
- DeepSeek V4 Pro — 750 tokens en entrée, 82,000 en cache, 290 tokens en sortie par requête
109+
- DeepSeek V4 Flash — 790 tokens en entrée, 68,000 en cache, 280 tokens en sortie par requête
109110
- MiniMax M2.7/M2.5 — 300 tokens en entrée, 55,000 en cache, 125 tokens en sortie par requête
110-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
111-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
111+
- Qwen3.5 Plus — 410 tokens en entrée, 47,000 en cache, 140 tokens en sortie par requête
112+
- Qwen3.6 Plus — 500 tokens en entrée, 57,000 en cache, 190 tokens en sortie par requête
112113
- MiMo-V2-Pro — 350 tokens en entrée, 41,000 en cache, 250 tokens en sortie par requête
113114
- MiMo-V2-Omni — 1000 tokens en entrée, 60,000 en cache, 140 tokens en sortie par requête
114115
- MiMo-V2.5-Pro — 350 tokens en entrée, 41,000 en cache, 250 tokens en sortie par requête

‎packages/web/src/content/docs/go.mdx‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -108,14 +108,15 @@ The table below provides an estimated request count based on typical Go usage pa
108108
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
109109
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
110110
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
111-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
112-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
111+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
112+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
113113

114114
Estimates are based on observed average request patterns:
115115

116116
- GLM-5/5.1 — 700 input, 52,000 cached, 150 output tokens per request
117117
- Kimi K2.5/K2.6 — 870 input, 55,000 cached, 200 output tokens per request
118-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
118+
- DeepSeek V4 Pro — 750 input, 82,000 cached, 290 output tokens per request
119+
- DeepSeek V4 Flash — 790 input, 68,000 cached, 280 output tokens per request
119120
- MiniMax M2.7/M2.5 — 300 input, 55,000 cached, 125 output tokens per request
120121
- MiMo-V2-Pro — 350 input, 41,000 cached, 250 output tokens per request
121122
- MiMo-V2-Omni — 1000 input, 60,000 cached, 140 output tokens per request

‎packages/web/src/content/docs/it/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -106,17 +106,18 @@ La tabella seguente fornisce una stima del conteggio delle richieste in base a p
106106
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
107107
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
108108
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
109-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
110-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
109+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
110+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
111111

112112
Le stime si basano sui pattern medi di richieste osservati:
113113

114114
- GLM-5/5.1 — 700 di input, 52.000 in cache, 150 token di output per richiesta
115115
- Kimi K2.5/K2.6 — 870 di input, 55.000 in cache, 200 token di output per richiesta
116-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
116+
- DeepSeek V4 Pro — 750 di input, 82.000 in cache, 290 token di output per richiesta
117+
- DeepSeek V4 Flash — 790 di input, 68.000 in cache, 280 token di output per richiesta
117118
- MiniMax M2.7/M2.5 — 300 di input, 55.000 in cache, 125 token di output per richiesta
118-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
119-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
119+
- Qwen3.5 Plus — 410 di input, 47.000 in cache, 140 token di output per richiesta
120+
- Qwen3.6 Plus — 500 di input, 57.000 in cache, 190 token di output per richiesta
120121
- MiMo-V2-Pro — 350 di input, 41.000 in cache, 250 token di output per richiesta
121122
- MiMo-V2-Omni — 1000 di input, 60.000 in cache, 140 token di output per richiesta
122123
- MiMo-V2.5-Pro — 350 di input, 41.000 in cache, 250 token di output per richiesta

‎packages/web/src/content/docs/ja/go.mdx‎

Lines changed: 6 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -98,17 +98,18 @@ OpenCode Goには以下の制限が含まれています：
9898
| MiniMax M2.5 | 6,300 | 15,900 | 31,800 |
9999
| Qwen3.6 Plus | 3,300 | 8,200 | 16,300 |
100100
| Qwen3.5 Plus | 10,200 | 25,200 | 50,500 |
101-
| DeepSeek V4 Pro | 1,300 | 3,250 | 6,500 |
102-
| DeepSeek V4 Flash | 7,450 | 18,600 | 37,300 |
101+
| DeepSeek V4 Pro | 3,450 | 8,550 | 17,150 |
102+
| DeepSeek V4 Flash | 5,750 | 14,350 | 28,650 |
103103

104104
推定値は、観測された平均的なリクエストパターンに基づいています：
105105

106106
- GLM-5/5.1 — リクエストあたり 入力 700トークン、キャッシュ 52,000トークン、出力 150トークン
107107
- Kimi K2.5/K2.6 — リクエストあたり 入力 870トークン、キャッシュ 55,000トークン、出力 200トークン
108-
- DeepSeek V4 Pro/Flash — 700 input, 52,000 cached, 150 output tokens per request
108+
- DeepSeek V4 Pro — リクエストあたり 入力 750トークン、キャッシュ 82,000トークン、出力 290トークン
109+
- DeepSeek V4 Flash — リクエストあたり 入力 790トークン、キャッシュ 68,000トークン、出力 280トークン
109110
- MiniMax M2.7/M2.5 — リクエストあたり 入力 300トークン、キャッシュ 55,000トークン、出力 125トークン
110-
- Qwen3.5 Plus — 410 input, 47,000 cached, 140 output tokens per request
111-
- Qwen3.6 Plus — 500 input, 57,000 cached, 190 output tokens per request
111+
- Qwen3.5 Plus — リクエストあたり 入力 410トークン、キャッシュ 47,000トークン、出力 140トークン
112+
- Qwen3.6 Plus — リクエストあたり 入力 500トークン、キャッシュ 57,000トークン、出力 190トークン
112113
- MiMo-V2-Pro — リクエストあたり 入力 350トークン、キャッシュ 41,000トークン、出力 250トークン
113114
- MiMo-V2-Omni — リクエストあたり 入力 1000トークン、キャッシュ 60,000トークン、出力 140トークン
114115
- MiMo-V2.5-Pro — リクエストあたり 入力 350トークン、キャッシュ 41,000トークン、出力 250トークン

0 commit comments

Comments
 (0)