4,757 个接口 · 10,634 个价格 · 最近采集 22 分钟前 · 30 天内 399 条需关注的调价
每个平台公布的每一个价格
采集器定时抓取 8 个平台公开的全部价格（默认每日一次），并完整保存原始页面快照，绝无任何手工篡改。搜索具体模型，即可查看当前各单位下的最低价格。
模型
Claude 
Gemini 
Qwen 
DeepSeek 
GLM 
Kimi 
Mistral 
MiniMax 
Hunyuan 
Nemotron 
Llama 第 201–300 条，共 594 条
每百万缓存读取 token100
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| OpenRouter第三方 | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint coreweave/fp4) | |
| OpenRouter官方 | Mistral: Mistral Large 3 2512via Mistral · zdr | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint mistral/zdr) | |
| OpenRouter官方 | OpenAI: GPT-4.1 Mini (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Sol Pro (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Sol (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-6.1 Terravia Azure | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint azure) | |
| OpenRouter官方合作 | OpenAI: GPT-6.1 Terra Provia Azure | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint azure) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Terra Pro (batch)提示词超过 272K | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (>272000; endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Terra (batch)提示词超过 272K | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (>272000; endpoint openai) | |
| OpenRouter第三方 | Reflection: Beam 1.0 501B A23Bvia Nebius · fp4 | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint nebius/fp4) | |
| OpenRouter未披露 | Anthropic: Claude Haiku Latest提示词超过 100K | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (>100000) | |
| OpenRouter未披露 | OpenAI: GPT Terra Latest | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token | |
| Runware未披露 | Claude Haiku 5.5> 100K context | $0.05/百万缓存读 | $5e-8 / cachedInputToken · > 100K context | |
| Runware未披露 | GPT-6.1 Terra≤ 272K context | $0.05/百万缓存读 | $5e-8 / cachedInputToken · ≤ 272K context | |
| OpenRouter官方 | Qwen: Qwen-Plus | $0.052/百万缓存读 | input_cache_read: 0.000000052 / token (endpoint alibaba) | |
| Aiberm未披露 | GPT-5.3 Codex | $0.054/百万缓存读 | model_ratio 0.39 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Aiberm未披露 | GPT-5.3 Codex | $0.054/百万缓存读 | model_ratio 0.39 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouter第三方 | Z.ai: GLM 4.6Vvia Novita · bf16 | $0.055/百万缓存读 | input_cache_read: 0.000000055 / token (endpoint novita/bf16) | |
| KIE未披露 | gpt-5.6-terra | $0.056/百万缓存读 | 11.2 credits per million tokens ($0.056)平台声称官方或 Fal 价 $0.2/百万缓存读 | |
| KIE未披露 | gpt-6-sol | $0.06/百万缓存读 | 12 credits per million tokens ($0.06)平台声称官方或 Fal 价 $0.2/百万缓存读 | |
| OpenRouter第三方 | Elorian: Glimpse | $0.06/百万缓存读 | input_cache_read: 0.00000006 / token (endpoint together) | |
| OpenRouter未披露 | Motif Technologies: Motif 3 | $0.06/百万缓存读 | input_cache_read: 0.00000006 / token (endpoint kt) | |
| OpenRouter第三方 | Tencent: Hy3 preview | $0.06/百万缓存读 | input_cache_read: 0.00000006 / token (endpoint gmicloud/bf16) | |
| Runware未披露 | MiniMax M3≤ 512K context | $0.06/百万缓存读 | $6e-8 / cachedInputToken · ≤ 512K context | |
| OpenRouter官方 | OpenAI: GPT-5.1 (batch) | $0.063/百万缓存读 | input_cache_read: 0.0000000625 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-5 (batch) | $0.063/百万缓存读 | input_cache_read: 0.0000000625 / token (endpoint openai) | |
| OpenRouter官方 | Qwen: Qwen3.7 Plusvia Alibaba | $0.064/百万缓存读 | input_cache_read: 0.000000064 / token (endpoint alibaba) | |
| OpenRouter官方 | Qwen: Qwen3 Coder Flash提示词超过 32K | $0.065/百万缓存读 | input_cache_read: 0.000000065 / token (>32000; endpoint alibaba) | |
| OpenRouter第三方 | MoonshotAI: Kimi K2.6via Baidu · fp4 | $0.066/百万缓存读 | input_cache_read: 0.0000000656 / token (endpoint baidu/fp4) | |
| OpenRouter未披露 | Z.ai: GLM Latest | $0.069/百万缓存读 | input_cache_read: 0.0000000689 / token | |
| Aiberm未披露 | Qwen3.5 Plus | $0.069/百万缓存读 | model_ratio 0.75 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Qwen3.6 Plus | $0.069/百万缓存读 | model_ratio 0.75 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| OpenRouter官方 | Mistral: Mistral Large 4via Mistral · zdr | $0.07/百万缓存读 | input_cache_read: 0.00000007 / token (endpoint mistral/zdr) | |
| OpenRouter第三方 | Qwen: Qwen3 Coder Next | $0.07/百万缓存读 | input_cache_read: 0.00000007 / token (endpoint parasail/bf16) | |
| Aiberm未披露 | Claude Sonnet 5.5 | $0.072/百万缓存读 | model_ratio 3.1304 × $2/M · group default ×0.23 · cache_ratio 0.05 | |
| Aiberm未披露 | Claude Opus 4.5 20251101 | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Opus 4.5 20251101 Thinking | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Opus 4.6 | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Opus 4.6 Thinking | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Opus 4.7 | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Opus 4.8 | $0.075/百万缓存读 | model_ratio 1.629 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter官方 | Google: Gemini 3.5 Flash (batch) | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.6 Flashvia Google AI Studio | $0.075/百万缓存读 | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.6 Flashvia Google AI Studio | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.7 Flashvia Google AI Studio | $0.075/百万缓存读 | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.7 Flashvia Google AI Studio | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.8 Flashvia Google AI Studio | $0.075/百万缓存读 | input_audio_cache: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.8 Flashvia Google AI Studio | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint google-ai-studio) | |
| OpenRouter官方合作 | OpenAI: GPT-4o-minivia Azure | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint azure) | |
| OpenRouter官方 | OpenAI: GPT-4o-mini (2024-07-18) | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-5.4 Minivia Azure | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint azure) | |
| OpenRouter官方 | Z.ai: GLM 5.3 FlashX | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint z-ai/fp8) | |
| OpenRouter官方 | Z.ai: GLM 5.3 FlashX Legal | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token (endpoint z-ai/fp8) | |
| OpenRouter未披露 | Google: Gemini Flash Latest | $0.075/百万缓存读 | input_audio_cache: 0.000000075 / token | |
| OpenRouter未披露 | Google: Gemini Flash Latest | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token | |
| OpenRouter未披露 | OpenAI: GPT Mini Latest | $0.075/百万缓存读 | input_cache_read: 0.000000075 / token | |
| Runware未披露 | Gemini 3.7 FlashPer 1M | $0.075/百万缓存读 | $7.5e-8 / cachedInputToken | |
| Runware未披露 | Gemini 3.8 FlashPer 1M | $0.075/百万缓存读 | $7.5e-8 / cachedInputToken | |
| Aiberm未披露 | o3 Mini | $0.076/百万缓存读 | model_ratio 0.55 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Runware未披露 | DeepSeek-V4-Pro-0813Per 1M | $0.079/百万缓存读 | $7.9e-8 / cachedInputToken | |
| KIE未披露 | Kimi K3.1 Pro | $0.08/百万缓存读 | 16 credits per million tokens ($0.08)平台声称官方或 Fal 价 $0.2/百万缓存读 | |
| OpenRouter第三方 | Thinking Machines: Inkling Small (batch) | $0.08/百万缓存读 | input_cache_read: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouter第三方 | Xiaomi: MiMo-V2.5 | $0.08/百万缓存读 | input_cache_read: 0.00000008 / token (endpoint venice/fp8) | |
| OpenRouter第三方 | Z.ai: GLM 4.6via Venice · fp4 | $0.08/百万缓存读 | input_cache_read: 0.00000008 / token (endpoint venice/fp4) | |
| OpenRouter第三方 | Z.ai: GLM 4.7via DeepInfra · fp4 | $0.08/百万缓存读 | input_cache_read: 0.00000008 / token (endpoint deepinfra/fp4) | |
| Aiberm未披露 | Kimi K2.5 | $0.083/百万缓存读 | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Kimi K2.6 | $0.083/百万缓存读 | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | GPT-5.2 Codex | $0.083/百万缓存读 | model_ratio 0.6 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Aiberm未披露 | Kimi K2.5 | $0.083/百万缓存读 | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Kimi K2.5 Thinking | $0.083/百万缓存读 | model_ratio 0.9 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | GPT-5.2 Codex | $0.083/百万缓存读 | model_ratio 0.6 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouter官方 | OpenAI: GPT-5.2 (batch) | $0.088/百万缓存读 | input_cache_read: 0.0000000875 / token (endpoint openai) | |
| Aiberm未披露 | Claude Sonnet | $0.088/百万缓存读 | model_ratio 1.917 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter第三方 | Z.ai: GLM 5.1via Chutes · fp8 | $0.09/百万缓存读 | input_cache_read: 0.00000009 / token (endpoint chutes/fp8) | |
| Aiberm未披露 | MiniMax M2.7 | $0.091/百万缓存读 | model_ratio 0.9852 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Gemini 3.5 Flash | $0.092/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Gemini 3.6 Flash | $0.092/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Gemini 3.7 Flash | $0.092/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Gemini 3.8 Flash | $0.092/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | MiMo V2 Omni | $0.092/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | Grok 4.5 | $0.095/百万缓存读 | model_ratio 0.8261 × $2/M · group default ×0.23 · cache_ratio 0.25 | |
| Aiberm未披露 | Grok 4.6 | $0.095/百万缓存读 | model_ratio 0.8261 × $2/M · group default ×0.23 · cache_ratio 0.25 | |
| Aiberm未披露 | GPT-5.6 Sol | $0.097/百万缓存读 | model_ratio 1.413 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| OpenRouter未披露 | DeepSeek: DeepSeek Pro Latest | $0.1/百万缓存读 | input_cache_read: 0.0000000999 / token | |
| OpenRouter官方 | Anthropic: Claude Fable 5.2 (batch) | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouter官方合作 | Anthropic: Claude Haiku 4.5via Azure · global | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint azure/global) | |
| OpenRouter官方 | Anthropic: Claude Opus 5.5 (batch) | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouter官方合作 | Anthropic: Claude Sonnet 5.5via Google · global | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Anthropic: Claude Sonnet 5 (batch) | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint anthropic) | |
| OpenRouter第三方 | ByteDance: UI-TARS 7B | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint parasail/bf16) | |
| OpenRouter官方 | Google: Gemini 2.5 Flashvia Google AI Studio | $0.1/百万缓存读 | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.1/百万缓存读 | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 4 Argon | $0.1/百万缓存读 | input_audio_cache: 0.0000001 / token | |
| OpenRouter官方 | Google: Gemini 4 Argon | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token | |
| OpenRouter官方 | Google: Gemini 4 Carbonvia Google AI Studio | $0.1/百万缓存读 | input_audio_cache: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 4 Carbonvia Google AI Studio | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint google-ai-studio) | |
| OpenRouter未披露 | Google: Gemma 4 31Bvia KT | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint kt) | |
| OpenRouter未披露 | NVIDIA: Nemotron 3 Ultravia KT | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint kt) | |
| OpenRouter官方合作 | OpenAI: GPT-4.1 Minivia Azure | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint azure) | |
| OpenRouter官方 | OpenAI: GPT-5.6 Terra Pro (batch) | $0.1/百万缓存读 | input_cache_read: 0.0000001 / token (endpoint openai) |
