Skip to content

Commit a5c517c

Browse files
longkeyylongkeyy
authored
feat: update ali models and price 20250213 (songquanpeng#2086)
1 parent 3f421c4 commit a5c517c

File tree

2 files changed

+103
-85
lines changed

2 files changed

+103
-85
lines changed

‎relay/adaptor/ali/constants.go

+4
Original file line numberDiff line numberDiff line change
@@ -14,10 +14,14 @@ var ModelList = []string{
1414
"qwen2-72b-instruct", "qwen2-57b-a14b-instruct", "qwen2-7b-instruct", "qwen2-1.5b-instruct", "qwen2-0.5b-instruct",
1515
"qwen1.5-110b-chat", "qwen1.5-72b-chat", "qwen1.5-32b-chat", "qwen1.5-14b-chat", "qwen1.5-7b-chat", "qwen1.5-1.8b-chat", "qwen1.5-0.5b-chat",
1616
"qwen-72b-chat", "qwen-14b-chat", "qwen-7b-chat", "qwen-1.8b-chat", "qwen-1.8b-longcontext-chat",
17+
"qvq-72b-preview",
18+
"qwen2.5-vl-72b-instruct", "qwen2.5-vl-7b-instruct", "qwen2.5-vl-2b-instruct", "qwen2.5-vl-1b-instruct", "qwen2.5-vl-0.5b-instruct",
1719
"qwen2-vl-7b-instruct", "qwen2-vl-2b-instruct", "qwen-vl-v1", "qwen-vl-chat-v1",
1820
"qwen2-audio-instruct", "qwen-audio-chat",
1921
"qwen2.5-math-72b-instruct", "qwen2.5-math-7b-instruct", "qwen2.5-math-1.5b-instruct", "qwen2-math-72b-instruct", "qwen2-math-7b-instruct", "qwen2-math-1.5b-instruct",
2022
"qwen2.5-coder-32b-instruct", "qwen2.5-coder-14b-instruct", "qwen2.5-coder-7b-instruct", "qwen2.5-coder-3b-instruct", "qwen2.5-coder-1.5b-instruct", "qwen2.5-coder-0.5b-instruct",
2123
"text-embedding-v1", "text-embedding-v3", "text-embedding-v2", "text-embedding-async-v2", "text-embedding-async-v1",
2224
"ali-stable-diffusion-xl", "ali-stable-diffusion-v1.5", "wanx-v1",
25+
"qwen-mt-plus", "qwen-mt-turbo",
26+
"deepseek-r1", "deepseek-v3", "deepseek-r1-distill-qwen-1.5b", "deepseek-r1-distill-qwen-7b", "deepseek-r1-distill-qwen-14b", "deepseek-r1-distill-qwen-32b", "deepseek-r1-distill-llama-8b", "deepseek-r1-distill-llama-70b",
2327
}

‎relay/billing/ratio/model.go

+99-85
Original file line numberDiff line numberDiff line change
@@ -159,91 +159,105 @@ var ModelRatio = map[string]float64{
159159
"embedding-2": 0.0005 * RMB,
160160
"embedding-3": 0.0005 * RMB,
161161
// https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
162-
"qwen-turbo": 1.4286, // ￥0.02 / 1k tokens
163-
"qwen-turbo-latest": 1.4286,
164-
"qwen-plus": 1.4286,
165-
"qwen-plus-latest": 1.4286,
166-
"qwen-max": 1.4286,
167-
"qwen-max-latest": 1.4286,
168-
"qwen-max-longcontext": 1.4286,
169-
"qwen-vl-max": 1.4286,
170-
"qwen-vl-max-latest": 1.4286,
171-
"qwen-vl-plus": 1.4286,
172-
"qwen-vl-plus-latest": 1.4286,
173-
"qwen-vl-ocr": 1.4286,
174-
"qwen-vl-ocr-latest": 1.4286,
175-
"qwen-audio-turbo": 1.4286,
176-
"qwen-math-plus": 1.4286,
177-
"qwen-math-plus-latest": 1.4286,
178-
"qwen-math-turbo": 1.4286,
179-
"qwen-math-turbo-latest": 1.4286,
180-
"qwen-coder-plus": 1.4286,
181-
"qwen-coder-plus-latest": 1.4286,
182-
"qwen-coder-turbo": 1.4286,
183-
"qwen-coder-turbo-latest": 1.4286,
184-
"qwq-32b-preview": 1.4286,
185-
"qwen2.5-72b-instruct": 1.4286,
186-
"qwen2.5-32b-instruct": 1.4286,
187-
"qwen2.5-14b-instruct": 1.4286,
188-
"qwen2.5-7b-instruct": 1.4286,
189-
"qwen2.5-3b-instruct": 1.4286,
190-
"qwen2.5-1.5b-instruct": 1.4286,
191-
"qwen2.5-0.5b-instruct": 1.4286,
192-
"qwen2-72b-instruct": 1.4286,
193-
"qwen2-57b-a14b-instruct": 1.4286,
194-
"qwen2-7b-instruct": 1.4286,
195-
"qwen2-1.5b-instruct": 1.4286,
196-
"qwen2-0.5b-instruct": 1.4286,
197-
"qwen1.5-110b-chat": 1.4286,
198-
"qwen1.5-72b-chat": 1.4286,
199-
"qwen1.5-32b-chat": 1.4286,
200-
"qwen1.5-14b-chat": 1.4286,
201-
"qwen1.5-7b-chat": 1.4286,
202-
"qwen1.5-1.8b-chat": 1.4286,
203-
"qwen1.5-0.5b-chat": 1.4286,
204-
"qwen-72b-chat": 1.4286,
205-
"qwen-14b-chat": 1.4286,
206-
"qwen-7b-chat": 1.4286,
207-
"qwen-1.8b-chat": 1.4286,
208-
"qwen-1.8b-longcontext-chat": 1.4286,
209-
"qwen2-vl-7b-instruct": 1.4286,
210-
"qwen2-vl-2b-instruct": 1.4286,
211-
"qwen-vl-v1": 1.4286,
212-
"qwen-vl-chat-v1": 1.4286,
213-
"qwen2-audio-instruct": 1.4286,
214-
"qwen-audio-chat": 1.4286,
215-
"qwen2.5-math-72b-instruct": 1.4286,
216-
"qwen2.5-math-7b-instruct": 1.4286,
217-
"qwen2.5-math-1.5b-instruct": 1.4286,
218-
"qwen2-math-72b-instruct": 1.4286,
219-
"qwen2-math-7b-instruct": 1.4286,
220-
"qwen2-math-1.5b-instruct": 1.4286,
221-
"qwen2.5-coder-32b-instruct": 1.4286,
222-
"qwen2.5-coder-14b-instruct": 1.4286,
223-
"qwen2.5-coder-7b-instruct": 1.4286,
224-
"qwen2.5-coder-3b-instruct": 1.4286,
225-
"qwen2.5-coder-1.5b-instruct": 1.4286,
226-
"qwen2.5-coder-0.5b-instruct": 1.4286,
227-
"text-embedding-v1": 0.05, // ￥0.0007 / 1k tokens
228-
"text-embedding-v3": 0.05,
229-
"text-embedding-v2": 0.05,
230-
"text-embedding-async-v2": 0.05,
231-
"text-embedding-async-v1": 0.05,
232-
"ali-stable-diffusion-xl": 8.00,
233-
"ali-stable-diffusion-v1.5": 8.00,
234-
"wanx-v1": 8.00,
235-
"SparkDesk": 1.2858, // ￥0.018 / 1k tokens
236-
"SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens
237-
"SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens
238-
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
239-
"SparkDesk-v3.1-128K": 1.2858, // ￥0.018 / 1k tokens
240-
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
241-
"SparkDesk-v3.5-32K": 1.2858, // ￥0.018 / 1k tokens
242-
"SparkDesk-v4.0": 1.2858, // ￥0.018 / 1k tokens
243-
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
244-
"embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens
245-
"embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens
246-
"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
162+
"qwen-turbo": 0.0003 * RMB,
163+
"qwen-turbo-latest": 0.0003 * RMB,
164+
"qwen-plus": 0.0008 * RMB,
165+
"qwen-plus-latest": 0.0008 * RMB,
166+
"qwen-max": 0.0024 * RMB,
167+
"qwen-max-latest": 0.0024 * RMB,
168+
"qwen-max-longcontext": 0.0005 * RMB,
169+
"qwen-vl-max": 0.003 * RMB,
170+
"qwen-vl-max-latest": 0.003 * RMB,
171+
"qwen-vl-plus": 0.0015 * RMB,
172+
"qwen-vl-plus-latest": 0.0015 * RMB,
173+
"qwen-vl-ocr": 0.005 * RMB,
174+
"qwen-vl-ocr-latest": 0.005 * RMB,
175+
"qwen-audio-turbo": 1.4286,
176+
"qwen-math-plus": 0.004 * RMB,
177+
"qwen-math-plus-latest": 0.004 * RMB,
178+
"qwen-math-turbo": 0.002 * RMB,
179+
"qwen-math-turbo-latest": 0.002 * RMB,
180+
"qwen-coder-plus": 0.0035 * RMB,
181+
"qwen-coder-plus-latest": 0.0035 * RMB,
182+
"qwen-coder-turbo": 0.002 * RMB,
183+
"qwen-coder-turbo-latest": 0.002 * RMB,
184+
"qwen-mt-plus": 0.015 * RMB,
185+
"qwen-mt-turbo": 0.001 * RMB,
186+
"qwq-32b-preview": 0.002 * RMB,
187+
"qwen2.5-72b-instruct": 0.004 * RMB,
188+
"qwen2.5-32b-instruct": 0.03 * RMB,
189+
"qwen2.5-14b-instruct": 0.001 * RMB,
190+
"qwen2.5-7b-instruct": 0.0005 * RMB,
191+
"qwen2.5-3b-instruct": 0.006 * RMB,
192+
"qwen2.5-1.5b-instruct": 0.0003 * RMB,
193+
"qwen2.5-0.5b-instruct": 0.0003 * RMB,
194+
"qwen2-72b-instruct": 0.004 * RMB,
195+
"qwen2-57b-a14b-instruct": 0.0035 * RMB,
196+
"qwen2-7b-instruct": 0.001 * RMB,
197+
"qwen2-1.5b-instruct": 0.001 * RMB,
198+
"qwen2-0.5b-instruct": 0.001 * RMB,
199+
"qwen1.5-110b-chat": 0.007 * RMB,
200+
"qwen1.5-72b-chat": 0.005 * RMB,
201+
"qwen1.5-32b-chat": 0.0035 * RMB,
202+
"qwen1.5-14b-chat": 0.002 * RMB,
203+
"qwen1.5-7b-chat": 0.001 * RMB,
204+
"qwen1.5-1.8b-chat": 0.001 * RMB,
205+
"qwen1.5-0.5b-chat": 0.001 * RMB,
206+
"qwen-72b-chat": 0.02 * RMB,
207+
"qwen-14b-chat": 0.008 * RMB,
208+
"qwen-7b-chat": 0.006 * RMB,
209+
"qwen-1.8b-chat": 0.006 * RMB,
210+
"qwen-1.8b-longcontext-chat": 0.006 * RMB,
211+
"qvq-72b-preview": 0.012 * RMB,
212+
"qwen2.5-vl-72b-instruct": 0.016 * RMB,
213+
"qwen2.5-vl-7b-instruct": 0.002 * RMB,
214+
"qwen2.5-vl-3b-instruct": 0.0012 * RMB,
215+
"qwen2-vl-7b-instruct": 0.016 * RMB,
216+
"qwen2-vl-2b-instruct": 0.002 * RMB,
217+
"qwen-vl-v1": 0.002 * RMB,
218+
"qwen-vl-chat-v1": 0.002 * RMB,
219+
"qwen2-audio-instruct": 0.002 * RMB,
220+
"qwen-audio-chat": 0.002 * RMB,
221+
"qwen2.5-math-72b-instruct": 0.004 * RMB,
222+
"qwen2.5-math-7b-instruct": 0.001 * RMB,
223+
"qwen2.5-math-1.5b-instruct": 0.001 * RMB,
224+
"qwen2-math-72b-instruct": 0.004 * RMB,
225+
"qwen2-math-7b-instruct": 0.001 * RMB,
226+
"qwen2-math-1.5b-instruct": 0.001 * RMB,
227+
"qwen2.5-coder-32b-instruct": 0.002 * RMB,
228+
"qwen2.5-coder-14b-instruct": 0.002 * RMB,
229+
"qwen2.5-coder-7b-instruct": 0.001 * RMB,
230+
"qwen2.5-coder-3b-instruct": 0.001 * RMB,
231+
"qwen2.5-coder-1.5b-instruct": 0.001 * RMB,
232+
"qwen2.5-coder-0.5b-instruct": 0.001 * RMB,
233+
"text-embedding-v1": 0.0007 * RMB, // ￥0.0007 / 1k tokens
234+
"text-embedding-v3": 0.0007 * RMB,
235+
"text-embedding-v2": 0.0007 * RMB,
236+
"text-embedding-async-v2": 0.0007 * RMB,
237+
"text-embedding-async-v1": 0.0007 * RMB,
238+
"ali-stable-diffusion-xl": 8.00,
239+
"ali-stable-diffusion-v1.5": 8.00,
240+
"wanx-v1": 8.00,
241+
"deepseek-r1": 0.002 * RMB,
242+
"deepseek-v3": 0.001 * RMB,
243+
"deepseek-r1-distill-qwen-1.5b": 0.001 * RMB,
244+
"deepseek-r1-distill-qwen-7b": 0.0005 * RMB,
245+
"deepseek-r1-distill-qwen-14b": 0.001 * RMB,
246+
"deepseek-r1-distill-qwen-32b": 0.002 * RMB,
247+
"deepseek-r1-distill-llama-8b": 0.0005 * RMB,
248+
"deepseek-r1-distill-llama-70b": 0.004 * RMB,
249+
"SparkDesk": 1.2858, // ￥0.018 / 1k tokens
250+
"SparkDesk-v1.1": 1.2858, // ￥0.018 / 1k tokens
251+
"SparkDesk-v2.1": 1.2858, // ￥0.018 / 1k tokens
252+
"SparkDesk-v3.1": 1.2858, // ￥0.018 / 1k tokens
253+
"SparkDesk-v3.1-128K": 1.2858, // ￥0.018 / 1k tokens
254+
"SparkDesk-v3.5": 1.2858, // ￥0.018 / 1k tokens
255+
"SparkDesk-v3.5-32K": 1.2858, // ￥0.018 / 1k tokens
256+
"SparkDesk-v4.0": 1.2858, // ￥0.018 / 1k tokens
257+
"360GPT_S2_V9": 0.8572, // ¥0.012 / 1k tokens
258+
"embedding-bert-512-v1": 0.0715, // ¥0.001 / 1k tokens
259+
"embedding_s1_v1": 0.0715, // ¥0.001 / 1k tokens
260+
"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
247261
// https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
248262
"hunyuan-turbo": 0.015 * RMB,
249263
"hunyuan-large": 0.004 * RMB,

0 commit comments

Comments
 (0)