4,759 个接口 · 10,896 个价格 · 最近采集 9 分钟前 · 30 天内 442 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 401–500 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 |
|---|---|---|---|---|
| Aiberm未披露 | MiMo V2 Pro | $0.193/百万缓存读 | model_ratio 2.1 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| Aiberm未披露 | GPT-6 Astra | $0.195/百万缓存读 | model_ratio 2.826 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| Aiberm未披露 | DeepSeek R1 0528 | $0.198/百万缓存读 | model_ratio 0.86 × $2/M · group default ×0.23 · cache_ratio 0.5 | |
| KIE未披露 | grok-4-6 | $0.2/百万缓存读 | 40 credits per million tokens ($0.20)平台声称官方或 Fal 价 $0.5/百万缓存读 | |
| KIE未披露 | grok-4-7 | $0.2/百万缓存读 | 40 credits per million tokens ($0.20)平台声称官方或 Fal 价 $0.5/百万缓存读 | |
| OpenRouter官方 | AionLabs: Aion-2.0 | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint aion-labs) | |
| OpenRouter官方合作 | Anthropic: Claude Fable 5.2via Google · global | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint google-vertex/global) | |
| OpenRouter官方合作 | Anthropic: Claude Opus 5.5via Amazon Bedrock | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint amazon-bedrock) | |
| OpenRouter官方合作 | Anthropic: Claude Sonnet 5via Claude Platform on AWS | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint claude-on-aws) | |
| OpenRouter官方 | Google: Gemini 3.1 Pro Previewvia Google · global | $0.2/百万缓存读 | input_audio_cache: 0.0000002 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.1 Pro Previewvia Google · global | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.1 Pro Preview Custom Tools | $0.2/百万缓存读 | input_audio_cache: 0.0000002 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.1 Pro Preview Custom Tools | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint google-ai-studio) | |
| OpenRouter第三方 | Meta: Muse Wondervia Google · global | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Mistral Largevia Mistral | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint mistral) | |
| OpenRouter官方 | Mistral Large 2407via Mistral · zdr | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint mistral/zdr) | |
| OpenRouter官方 | Mistral: Mixtral 8x22B Instructvia Mistral · zdr | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint mistral/zdr) | |
| OpenRouter第三方 | MoonshotAI: Kimi K2.5via AtlasCloud · int4 | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint atlas-cloud/int4) | |
| OpenRouter第三方 | MoonshotAI: Kimi K3.1 Provia Relace · fp4 | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint relace/fp4) | |
| OpenRouter第三方 | Nous: Hermes 4 405B | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint nebius/fp8) | |
| OpenRouter官方 | OpenAI: GPT-5.6 Sol Pro (batch) | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-5.6 Sol (batch) | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-5.6 Terravia Azure | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint azure) | |
| OpenRouter官方合作 | OpenAI: GPT-5.6 Terra Provia Azure | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint azure) | |
| OpenRouter官方 | OpenAI: GPT-5.6 Terra Pro (batch)提示词超过 272K | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-5.6 Terra (batch)提示词超过 272K | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-6 Solvia Amazon Bedrock · global | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint amazon-bedrock/global) | |
| OpenRouter官方合作 | OpenAI: GPT-6 Sol Provia OpenAI | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6 Sol Pro (batch)提示词超过 272K | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6 Sol (batch)提示词超过 272K | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-6.1 Sol提示词超过 272Kvia Amazon Bedrock · global | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouter官方合作 | OpenAI: GPT-6.1 Sol Pro提示词超过 272Kvia Azure | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000; endpoint azure) | |
| OpenRouter第三方 | ReMM SLERP 13B | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint mancer/fp8) | |
| OpenRouter官方 | SpaceXAI: Grok 4.20via xAI · zdr | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint xai/zdr) | |
| OpenRouter官方 | SpaceXAI: Grok 4.20 Multi-Agentvia xAI · zdr | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint xai/zdr) | |
| OpenRouter官方 | SpaceXAI: Grok 4.3via xAI · zdr | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint xai/zdr) | |
| OpenRouter官方 | SpaceXAI: Grok Build 0.1via xAI | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (endpoint xai) | |
| OpenRouter未披露 | Anthropic: Claude Fable Latest | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token | |
| OpenRouter未披露 | Anthropic: Claude Opus Latest | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token | |
| OpenRouter未披露 | OpenAI: GPT Sol Latest提示词超过 272K | $0.2/百万缓存读 | input_cache_read: 0.0000002 / token (>272000) | |
| Runware未披露 | Claude Fable 5.2Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | Claude Opus 5.5Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | Claude Sonnet 5Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | Claude Sonnet 5.5Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | Gemini 4 ArgonFrom Dec 1 · 2026 | $0.2/百万缓存读 | $2e-7 / cachedInputToken · From Dec 1, 2026 | |
| Runware未披露 | Kimi K3.1 ProPer 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | GPT-5.6 TerraPer 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | GPT-6.1 Sol> 272K context | $0.2/百万缓存读 | $2e-7 / cachedInputToken · > 272K context | |
| Runware未披露 | GPT-6 Sol≤ 272K context | $0.2/百万缓存读 | $2e-7 / cachedInputToken · ≤ 272K context | |
| Runware未披露 | Grok 4.3Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Runware未披露 | GLM-5.3Per 1M | $0.2/百万缓存读 | $2e-7 / cachedInputToken | |
| Aiberm未披露 | GPT-5.2 | $0.207/百万缓存读 | model_ratio 1.5 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Aiberm未披露 | GPT-5.4 xhigh | $0.207/百万缓存读 | model_ratio 1.5 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Aiberm未披露 | GPT-5.2 | $0.207/百万缓存读 | model_ratio 1.5 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| Aiberm未披露 | GPT-5.2 Chat | $0.207/百万缓存读 | model_ratio 1.5 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouter第三方 | MoonshotAI: Kimi K3 (batch) | $0.228/百万缓存读 | input_cache_read: 0.000000228 / token (endpoint deepinfra/bf16) | |
| Aiberm未披露 | Claude Sonnet 4.5 | $0.239/百万缓存读 | model_ratio 5.2 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.5 Thinking | $0.239/百万缓存读 | model_ratio 5.2 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.6 | $0.239/百万缓存读 | model_ratio 5.2 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.6 Thinking | $0.239/百万缓存读 | model_ratio 5.2 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| KIE未披露 | Kimi K3 | $0.24/百万缓存读 | 48 credits per million tokens ($0.24)平台声称官方或 Fal 价 $0.3/百万缓存读 | |
| OpenRouter官方 | Z.ai: GLM 5 Turbo | $0.24/百万缓存读 | input_cache_read: 0.00000024 / token (endpoint z-ai) | |
| OpenRouter官方 | Z.ai: GLM 5V Turbo | $0.24/百万缓存读 | input_cache_read: 0.00000024 / token (endpoint z-ai/fp8) | |
| OpenRouter官方合作 | Anthropic: Claude Fable 5.1via Azure | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint azure) | |
| OpenRouter官方 | Anthropic: Claude Opus 4.5 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint anthropic) | |
| OpenRouter官方 | Anthropic: Claude Opus 4.6 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint anthropic) | |
| OpenRouter官方 | Anthropic: Claude Opus 4.7 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint anthropic) | |
| OpenRouter官方 | Anthropic: Claude Opus 4.8 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint anthropic) | |
| OpenRouter官方 | Anthropic: Claude Opus 5 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint anthropic) | |
| OpenRouter第三方 | DeepSeek: DeepSeek V4 Pro 0423via Relace · fp4 | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint relace/fp4) | |
| OpenRouter官方 | Google: Gemini 2.5 Pro提示词超过 200Kvia Google AI Studio | $0.25/百万缓存读 | input_audio_cache: 0.00000025 / token (>200000; endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 2.5 Pro提示词超过 200Kvia Google AI Studio | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (>200000; endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 2.5 Pro Preview 06-05提示词超过 200Kvia Google AI Studio | $0.25/百万缓存读 | input_audio_cache: 0.00000025 / token (>200000; endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 2.5 Pro Preview 06-05提示词超过 200Kvia Google AI Studio | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (>200000; endpoint google-ai-studio) | |
| OpenRouter官方 | OpenAI: GPT-4.1 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint openai) | |
| OpenRouter官方合作 | OpenAI: GPT-5.4via Azure | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint azure) | |
| OpenRouter官方 | OpenAI: GPT-5.4 (batch)提示词超过 272K | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (>272000; endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-5.5 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: o3 (batch) | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint openai) | |
| OpenRouter第三方 | Qwen: Qwen3.8 2.4T A95Bvia Novita | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint novita) | |
| OpenRouter官方 | Qwen: Qwen3.8 Max (0902)via Alibaba | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint alibaba) | |
| OpenRouter官方 | Sakana: Fugu Max | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint sakana) | |
| OpenRouter第三方 | TheDrummer: Skyfall 36B V2 | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint parasail/fp8) | |
| OpenRouter官方 | Pareto 26.9 | $0.25/百万缓存读 | input_cache_read: 0.00000025 / token (endpoint unbiased) | |
| Runware未披露 | Claude Fable 5.1Per 1M | $0.25/百万缓存读 | $2.5e-7 / cachedInputToken | |
| OpenRouter第三方 | Qwen: Qwen3.5-27Bvia AtlasCloud · fp8 | $0.27/百万缓存读 | input_cache_read: 0.00000027 / token (endpoint atlas-cloud/fp8) | |
| OpenRouter官方 | OpenAI: o3 Mini (batch) | $0.275/百万缓存读 | input_cache_read: 0.000000275 / token (endpoint openai) | |
| Aiberm未披露 | GLM-5.2 | $0.276/百万缓存读 | model_ratio 2.4 × $2/M · group default ×0.23 · cache_ratio 0.25 | |
| KIE未披露 | gpt-6-astra | $0.28/百万缓存读 | 56 credits per million tokens ($0.28)平台声称官方或 Fal 价 $1/百万缓存读 | |
| Aiberm未披露 | Claude Opus 5.5 | $0.294/百万缓存读 | model_ratio 6.4 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter官方 | Qwen: Qwen3.7 Maxvia Alibaba | $0.295/百万缓存读 | input_cache_read: 0.000000295 / token (endpoint alibaba) | |
| OpenRouter官方合作 | Anthropic: Claude Sonnet 4.5via Claude Platform on AWS | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (endpoint claude-on-aws) | |
| OpenRouter官方 | Anthropic: Claude Sonnet 4.5 (batch)提示词超过 200K | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (>200000; endpoint anthropic) | |
| OpenRouter官方合作 | Anthropic: Claude Sonnet 4.6via Claude Platform on AWS | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (endpoint claude-on-aws) | |
| OpenRouter官方 | Fireworks: Ember-1 | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (endpoint fireworks) | |
| OpenRouter官方 | Google: Gemini 3.5 Flashvia Google · global | $0.3/百万缓存读 | input_audio_cache: 0.0000003 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Mancer: Weaver (alpha) | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (endpoint mancer/fp8) | |
| OpenRouter官方 | SpaceXAI: Grok 4.5via xAI · zdr | $0.3/百万缓存读 | input_cache_read: 0.0000003 / token (endpoint xai/zdr) | |
| Runware未披露 | Claude Sonnet 4.6Per 1M | $0.3/百万缓存读 | $3e-7 / cachedInputToken | |
| Runware未披露 | Kimi K3Per 1M | $0.3/百万缓存读 | $3e-7 / cachedInputToken |
