跳到正文
API Pricing

调价记录

每次采集到的价格与上一次不同，都会记录在这里。涨跌 30% 以上、计价单位变化、价格消失都会被标出。

只看需关注 383调价 362单位变化 145消失 121新增 1,066OpenRouterKIEFalWaveSpeedReplicateAPIMartRunware
时间模型 · 计价项变化
2026-11-10 11:07 UTCOpenRouterOpenAI: gpt-oss-20b调价需关注$0.09/百万输出 → $0.13/百万输出+44%completion: 0.00000009 / token → completion: 0.00000013 / token
2026-11-10 11:07 UTCOpenRouterOpenAI: gpt-oss-20b调价需关注$0.018/百万输入 → $0.03/百万输入+67%prompt: 0.000000018 / token → prompt: 0.00000003 / token
2026-11-10 11:07 UTCOpenRouterGoogle: Gemma 4 26B A4B 调价需关注$0.3/百万输出 → $0.1/百万输出−67%completion: 0.0000003 / token → completion: 0.0000001 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.2缓存读取调价需关注$0.005/百万缓存读 → $0.009/百万缓存读+80%input_cache_read: 0.000000005 / token → input_cache_read: 0.000000009 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.2调价需关注$0.006/百万输入 → $0.01/百万输入+67%prompt: 0.000000006 / token → prompt: 0.00000001 / token
2026-11-10 11:07 UTCOpenRouterMoonshotAI: Kimi K3 (batch)调价需关注$6/百万输出 → $11.4/百万输出+90%completion: 0.000006 / token → completion: 0.0000114 / token
2026-11-10 11:07 UTCOpenRouterMoonshotAI: Kimi K3 (batch)调价需关注$0.917/百万输入 → $2.28/百万输入+149%prompt: 0.000000917 / token → prompt: 0.00000228 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.3 Flash (batch)调价需关注$0.18/百万输出 → $0.061/百万输出−66%completion: 0.00000018 / token → completion: 0.000000061 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.3 Flash (batch)调价需关注$0.05/百万输入 → $0.03/百万输入−40%prompt: 0.00000005 / token → prompt: 0.00000003 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.3 Flash调价需关注$0.083/百万输出 → $0.5/百万输出+502%completion: 0.000000083 / token → completion: 0.0000005 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.3 Flash调价需关注$0.0335/百万输入 → $0.15/百万输入+348%prompt: 0.0000000335 / token → prompt: 0.00000015 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash (batch)缓存读取调价需关注$0.002/百万缓存读 → $0.00336/百万缓存读+68%input_cache_read: 0.000000002 / token → input_cache_read: 0.00000000336 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash (batch)调价需关注$0.2/百万输出 → $0.336/百万输出+68%completion: 0.0000002 / token → completion: 0.000000336 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash (batch)调价需关注$0.011/百万输入 → $0.112/百万输入+918%prompt: 0.000000011 / token → prompt: 0.000000112 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash缓存读取调价需关注$0.018/百万缓存读 → $0.005/百万缓存读−72%input_cache_read: 0.000000018 / token → input_cache_read: 0.000000005 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash调价需关注$0.051/百万输入 → $0.006/百万输入−88%prompt: 0.000000051 / token → prompt: 0.000000006 / token
2026-11-10 11:07 UTCOpenRouterMeta: Llama 3.3 70B Instruct调价$0.79/百万输出 → $0.71/百万输出−10%completion: 0.00000079 / token → completion: 0.00000071 / token
2026-11-10 11:07 UTCOpenRouterMeta: Llama 3.3 70B Instruct调价$0.59/百万输入 → $0.71/百万输入+20%prompt: 0.00000059 / token → prompt: 0.00000071 / token
2026-11-10 11:07 UTCOpenRouterQwen: Qwen3 14B调价$0.24/百万输出 → $0.22/百万输出−8%completion: 0.00000024 / token → completion: 0.00000022 / token
2026-11-10 11:07 UTCOpenRouterQwen: Qwen3 14B调价$0.12/百万输入 → $0.1/百万输入−17%prompt: 0.00000012 / token → prompt: 0.0000001 / token
2026-11-10 11:07 UTCOpenRouterGoogle: Gemma 4 26B A4B 缓存读取调价$0.05/百万缓存读 → $0.046/百万缓存读−8%input_cache_read: 0.00000005 / token → input_cache_read: 0.000000046 / token
2026-11-10 11:07 UTCOpenRouterGoogle: Gemma 4 26B A4B 调价$0.09/百万输入 → $0.08/百万输入−11%prompt: 0.00000009 / token → prompt: 0.00000008 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423缓存读取调价$0.074501/百万缓存读 → $0.079605/百万缓存读+7%input_cache_read: 0.000000074501 / token → input_cache_read: 0.000000079605 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423调价$1.78802/百万输出 → $1.91052/百万输出+7%completion: 0.000001788024 / token → completion: 0.00000191052 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423调价$0.894012/百万输入 → $0.95526/百万输入+7%prompt: 0.000000894012 / token → prompt: 0.00000095526 / token
2026-11-10 11:07 UTCOpenRouterMoonshotAI: Kimi Latest调价$9.3388/百万输出 → $10.5601/百万输出+13%completion: 0.0000093388 / token → completion: 0.0000105601 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable Latest缓存写入（1 小时）调价$20/百万缓存写 → $16/百万缓存写−20%input_cache_write_1h: 0.00002 / token → input_cache_write_1h: 0.000016 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable Latest缓存写入（5 分钟）调价$12.5/百万缓存写 → $10/百万缓存写−20%input_cache_write: 0.0000125 / token → input_cache_write: 0.00001 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable Latest缓存读取调价$0.25/百万缓存读 → $0.2/百万缓存读−20%input_cache_read: 0.00000025 / token → input_cache_read: 0.0000002 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable Latest调价$50/百万输出 → $40/百万输出−20%completion: 0.00005 / token → completion: 0.00004 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable Latest调价$10/百万输入 → $8/百万输入−20%prompt: 0.00001 / token → prompt: 0.000008 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.2 (batch)缓存读取调价$0.21/百万缓存读 → $0.178/百万缓存读−15%input_cache_read: 0.00000021 / token → input_cache_read: 0.000000178 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.2 (batch)调价$1.271/百万输出 → $1.075/百万输出−15%completion: 0.000001271 / token → completion: 0.000001075 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.2 (batch)调价$0.623/百万输入 → $0.527/百万输入−15%prompt: 0.000000623 / token → prompt: 0.000000527 / token
2026-11-10 11:07 UTCOpenRouterMoonshotAI: Kimi K3 (batch)缓存读取调价$0.226/百万缓存读 → $0.228/百万缓存读+1%input_cache_read: 0.000000226 / token → input_cache_read: 0.000000228 / token
2026-11-10 11:07 UTCOpenRouterZ.ai: GLM 5.3 Flash (batch)缓存读取调价$0.01/百万缓存读 → $0.013/百万缓存读+30%input_cache_read: 0.00000001 / token → input_cache_read: 0.000000013 / token
2026-11-10 11:07 UTCOpenRouterQwen: Qwen3.8 Max (0902) (batch)新增$3.45/百万输出completion: 0.00000345 / token
2026-11-10 11:07 UTCOpenRouterQwen: Qwen3.8 Max (0902) (batch)新增$1.15/百万输入prompt: 0.00000115 / token
2026-11-10 11:07 UTCOpenRouterDeepSeek: DeepSeek V4.1 Flash调价$0.567/百万输出 → $0.5/百万输出−12%completion: 0.000000567 / token → completion: 0.0000005 / token
2026-11-10 11:07 UTCOpenRouterNVIDIA: Nemotron 3.5 Super VL调价$0.5/百万输出 → $0.47/百万输出−6%completion: 0.0000005 / token → completion: 0.00000047 / token
2026-11-10 11:07 UTCOpenRouterMeta: Muse Ember缓存写入（5 分钟）新增$0.125/百万缓存写input_cache_write: 0.000000125 / token
2026-11-10 11:07 UTCOpenRouterMeta: Muse Ember缓存读取新增$0.004/百万缓存读input_cache_read: 0.000000004 / token
2026-11-10 11:07 UTCOpenRouterMeta: Muse Ember联网搜索新增$0.0025/次web_search: 0.0025
2026-11-10 11:07 UTCOpenRouterMeta: Muse Ember新增$0.5/百万输出completion: 0.0000005 / token
2026-11-10 11:07 UTCOpenRouterMeta: Muse Ember新增$0.1/百万输入prompt: 0.0000001 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)缓存写入（1 小时）新增$8/百万缓存写input_cache_write_1h: 0.000008 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)缓存写入（5 分钟）新增$5/百万缓存写input_cache_write: 0.000005 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)缓存读取新增$0.1/百万缓存读input_cache_read: 0.0000001 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)联网搜索新增$0.01/次web_search: 0.01
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)新增$20/百万输出completion: 0.00002 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2 (batch)新增$4/百万输入prompt: 0.000004 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2缓存写入（1 小时）新增$16/百万缓存写input_cache_write_1h: 0.000016 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2缓存写入（5 分钟）新增$10/百万缓存写input_cache_write: 0.00001 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2缓存读取新增$0.2/百万缓存读input_cache_read: 0.0000002 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2联网搜索新增$0.01/次web_search: 0.01
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2新增$40/百万输出completion: 0.00004 / token
2026-11-10 11:07 UTCOpenRouterAnthropic: Claude Fable 5.2新增$8/百万输入prompt: 0.000008 / token
2026-11-10 11:07 UTCOpenRouterThinking Machines: Inkling 2 Small (free)新增$0/百万输出completion: 0 / token
2026-11-10 11:07 UTCOpenRouterThinking Machines: Inkling 2 Small (free)新增$0/百万输入prompt: 0 / token
2026-11-10 11:07 UTCOpenRouterNex AGI: Nex-N2.6缓存读取新增$0.024/百万缓存读input_cache_read: 0.000000024 / token
2026-11-10 11:07 UTCOpenRouterNex AGI: Nex-N2.6新增$0.4/百万输出completion: 0.0000004 / token
2026-11-10 11:07 UTCOpenRouterNex AGI: Nex-N2.6新增$0.12/百万输入prompt: 0.00000012 / token
2026-11-09 14:03 UTCOpenRouterMeta: Llama 3.1 8B Instruct缓存读取消失需关注$0.025/百万缓存读input_cache_read: 0.000000025 / token
2026-11-09 14:03 UTCOpenRouterMeta: Llama 3.1 8B Instruct调价需关注$0.08/百万输出 → $0.04/百万输出−50%completion: 0.00000008 / token → completion: 0.00000004 / token
2026-11-09 14:03 UTCOpenRouterMeta: Llama 3.1 8B Instruct调价需关注$0.05/百万输入 → $0.02/百万输入−60%prompt: 0.00000005 / token → prompt: 0.00000002 / token
2026-11-09 14:03 UTCOpenRouterMistral: Mistral Small 3.2 24B调价需关注$0.2/百万输出 → $0.3/百万输出+50%completion: 0.0000002 / token → completion: 0.0000003 / token
2026-11-09 14:03 UTCOpenRouterMistral: Mistral Small 3.2 24B调价需关注$0.075/百万输入 → $0.1/百万输入+33%prompt: 0.000000075 / token → prompt: 0.0000001 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 4.5 Air调价需关注$0.13/百万输入 → $0.2/百万输入+54%prompt: 0.00000013 / token → prompt: 0.0000002 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-20b缓存读取调价需关注$0.03/百万缓存读 → $0.009/百万缓存读−70%input_cache_read: 0.00000003 / token → input_cache_read: 0.000000009 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-20b调价需关注$0.13/百万输出 → $0.09/百万输出−31%completion: 0.00000013 / token → completion: 0.00000009 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-20b调价需关注$0.03/百万输入 → $0.018/百万输入−40%prompt: 0.00000003 / token → prompt: 0.000000018 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-120b缓存读取调价需关注$0.023/百万缓存读 → $0.075/百万缓存读+226%input_cache_read: 0.000000023 / token → input_cache_read: 0.000000075 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-120b调价需关注$0.094/百万输出 → $0.6/百万输出+538%completion: 0.000000094 / token → completion: 0.0000006 / token
2026-11-09 14:03 UTCOpenRouterOpenAI: gpt-oss-120b调价需关注$0.025/百万输入 → $0.15/百万输入+500%prompt: 0.000000025 / token → prompt: 0.00000015 / token
2026-11-09 14:03 UTCOpenRouterQwen: Qwen3.5 397B A17B缓存读取调价需关注$0.3/百万缓存读 → $0.12/百万缓存读−60%input_cache_read: 0.0000003 / token → input_cache_read: 0.00000012 / token
2026-11-09 14:03 UTCOpenRouterGoogle: Gemma 4 26B A4B 缓存读取调价需关注$0.0375/百万缓存读 → $0.05/百万缓存读+33%input_cache_read: 0.0000000375 / token → input_cache_read: 0.00000005 / token
2026-11-09 14:03 UTCOpenRouterGoogle: Gemma 4 26B A4B 调价需关注$0.225/百万输出 → $0.3/百万输出+33%completion: 0.000000225 / token → completion: 0.0000003 / token
2026-11-09 14:03 UTCOpenRouterGoogle: Gemma 4 26B A4B 调价需关注$0.0675/百万输入 → $0.09/百万输入+33%prompt: 0.0000000675 / token → prompt: 0.00000009 / token
2026-11-09 14:03 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423缓存读取调价需关注$0.0192705/百万缓存读 → $0.074501/百万缓存读+287%input_cache_read: 0.0000000192705 / token → input_cache_read: 0.000000074501 / token
2026-11-09 14:03 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423调价需关注$0.462492/百万输出 → $1.78802/百万输出+287%completion: 0.000000462492 / token → completion: 0.000001788024 / token
2026-11-09 14:03 UTCOpenRouterDeepSeek: DeepSeek V4 Pro 0423调价需关注$0.231246/百万输入 → $0.894012/百万输入+287%prompt: 0.000000231246 / token → prompt: 0.000000894012 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.2 (batch)缓存读取调价需关注$0.115/百万缓存读 → $0.21/百万缓存读+83%input_cache_read: 0.000000115 / token → input_cache_read: 0.00000021 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.2 (batch)调价需关注$0.341/百万输入 → $0.623/百万输入+83%prompt: 0.000000341 / token → prompt: 0.000000623 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.3 (batch)调价需关注$1.381/百万输出 → $2/百万输出+45%completion: 0.000001381 / token → completion: 0.000002 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.3 (batch)调价需关注$0.341/百万输入 → $0.45/百万输入+32%prompt: 0.000000341 / token → prompt: 0.00000045 / token
2026-11-09 14:03 UTCOpenRouterGoogle: Gemma 3 27B调价$0.35/百万输出 → $0.45/百万输出+29%completion: 0.00000035 / token → completion: 0.00000045 / token
2026-11-09 14:03 UTCOpenRouterMistral: Mistral Small 3.2 24B缓存读取新增$0.01/百万缓存读input_cache_read: 0.00000001 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 4.5 Air缓存读取调价$0.025/百万缓存读 → $0.03/百万缓存读+20%input_cache_read: 0.000000025 / token → input_cache_read: 0.00000003 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 4.5 Air调价$0.85/百万输出 → $1.1/百万输出+29%completion: 0.00000085 / token → completion: 0.0000011 / token
2026-11-09 14:03 UTCOpenRouterQwen: Qwen3.5 397B A17B调价$0.5/百万输入 → $0.6/百万输入+20%prompt: 0.0000005 / token → prompt: 0.0000006 / token
2026-11-09 14:03 UTCOpenRouterMoonshotAI: Kimi Latest缓存读取调价$0.15/百万缓存读 → $0.18/百万缓存读+20%input_cache_read: 0.00000015 / token → input_cache_read: 0.00000018 / token
2026-11-09 14:03 UTCOpenRouterMoonshotAI: Kimi Latest调价$10.5634/百万输出 → $9.3388/百万输出−12%completion: 0.0000105634 / token → completion: 0.0000093388 / token
2026-11-09 14:03 UTCOpenRouterMoonshotAI: Kimi Latest调价$0.151/百万输入 → $0.1824/百万输入+21%prompt: 0.000000151 / token → prompt: 0.0000001824 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.2 (batch)调价$1.381/百万输出 → $1.271/百万输出−8%completion: 0.000001381 / token → completion: 0.000001271 / token
2026-11-09 14:03 UTCOpenRouterZ.ai: GLM 5.3 (batch)缓存读取调价$0.115/百万缓存读 → $0.1/百万缓存读−13%input_cache_read: 0.000000115 / token → input_cache_read: 0.0000001 / token
2026-11-08 14:03 UTCOpenRouterInception: Mercury 3消失需关注$0.1/百万输入prompt: 0.0000001 / token
2026-11-08 14:03 UTCOpenRouterInception: Mercury 3缓存读取消失需关注$0.01/百万缓存读input_cache_read: 0.00000001 / token
2026-11-08 14:03 UTCOpenRouterInception: Mercury 3消失需关注$0.35/百万输出completion: 0.00000035 / token
2026-11-08 14:03 UTCOpenRouterInception: Mercury 2.5消失需关注$0.04/百万输入prompt: 0.00000004 / token
2026-11-08 14:03 UTCOpenRouterInception: Mercury 2.5缓存读取消失需关注$0.004/百万缓存读input_cache_read: 0.000000004 / token

采集状态

平台模型数价格数频率最近一次状态
OpenRouter5542,314每天2026-11-11 12:09 UTC · 1 小时前正常
KIE232664每天2026-11-11 12:09 UTC · 1 小时前正常
Fal1,4701,895每天2026-11-11 12:24 UTC · 1 小时前正常
WaveSpeed1,1372,072每天2026-11-11 12:10 UTC · 1 小时前正常
Replicate435974每天2026-11-11 12:10 UTC · 1 小时前正常
APIMart3601,100每天2026-11-11 12:10 UTC · 1 小时前正常
Runware4161,116每天2026-11-11 13:02 UTC · 35 分钟前正常

每个平台的读取频率在采集后台设定，默认每天一次。时间为 UTC。