4,757 个接口 · 10,634 个价格 · 最近采集 23 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 101–200 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 | DeepSeek V3.2 | $0.021/百万缓存读 | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | DeepSeek V3.2 Exp | $0.021/百万缓存读 | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | DeepSeek V3.2 Exp Thinking | $0.021/百万缓存读 | model_ratio 0.45 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | GPT-5 Mini | $0.021/百万缓存读 | model_ratio 0.15 × $2/M · group default ×0.23 · cache_ratio 0.3 | |
| OpenRouter第三方 | DeepSeek: DeepSeek V4 Pro 0813via Baidu · fp8 | $0.021/百万缓存读 | input_cache_read: 0.000000020958 / token (endpoint baidu/fp8) | |
| OpenRouter第三方 | Qwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8 | $0.021/百万缓存读 | input_cache_read: 0.000000021 / token (endpoint primeintellect/fp8) | |
| OpenRouter官方 | Tencent: Hy4 | $0.021/百万缓存读 | input_cache_read: 0.000000021 / token (endpoint tencent/fp4) | |
| OpenRouter第三方 | DeepSeek: DeepSeek V3.2via GMICloud · fp8 | $0.022/百万缓存读 | input_cache_read: 0.0000000216 / token (endpoint gmicloud/fp8) | |
| OpenRouter官方 | Nex AGI: Nex-N2.6 | $0.024/百万缓存读 | input_cache_read: 0.000000024 / token (endpoint nex-agi/fp8) | |
| OpenRouter官方 | Anthropic: Claude Haiku 5.5 (batch)提示词超过 100K | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (>100000; endpoint anthropic) | |
| OpenRouter官方 | Google: Gemini 3.1 Flash Litevia Google AI Studio | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.1 Flash Lite Previewvia Google AI Studio | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.1 Flash Lite (batch) | $0.025/百万缓存读 | input_audio_cache: 0.000000025 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | LiquidAI: LFM2.5-24B-A2B | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint liquid/fp8) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Terra Pro (batch) | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-6.1 Terra (batch) | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint openai) | |
| OpenRouter第三方 | Qwen: Qwen3.6 27Bvia Chutes · fp8 | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint chutes/fp8) | |
| OpenRouter第三方 | Ricursive: Ripple 65B Previewvia PrimeIntellect · bf16 | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint primeintellect/bf16) | |
| OpenRouter第三方 | Z.ai: GLM 4.5 Airvia Novita · bf16 | $0.025/百万缓存读 | input_cache_read: 0.000000025 / token (endpoint novita/bf16) | |
| Aiberm未披露 | GPT-5.1 Codex Max | $0.028/百万缓存读 | model_ratio 0.6 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | DeepSeek V4 Flash | $0.029/百万缓存读 | model_ratio 0.3126 × $2/M · group default ×0.23 · cache_ratio 0.2 | |
| KIE未披露 | gpt-6-1-sol | $0.03/百万缓存读 | 6 credits per million tokens ($0.03)平台声称官方或 Fal 价 $0.1/百万缓存读 | |
| OpenRouter官方 | Google: Gemini 2.5 Flashvia Google AI Studio | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 2.5 Flash Litevia Google AI Studio | $0.03/百万缓存读 | input_audio_cache: 0.00000003 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.5 Flash Litevia Google AI Studio | $0.03/百万缓存读 | input_audio_cache: 0.00000003 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.5 Flash Litevia Google AI Studio | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Inference.net: Schematron V2 Turbovia InferenceNet · bf16 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint inference-net/bf16) | |
| OpenRouter第三方 | MiniMax: MiniMax M2.5via Venice | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint venice) | |
| OpenRouter官方 | Mistral: Codestral 2508via Mistral | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint mistral) | |
| OpenRouter官方合作 | OpenAI: GPT-4.1 Nanovia Azure | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint azure) | |
| OpenRouter官方合作 | OpenAI: GPT-5 Minivia Azure | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint azure) | |
| OpenRouter官方合作 | OpenAI: GPT-5.1-Codex-Mini | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter官方 | Pareto 26.10 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter未披露 | Upstage: Solar Pro 4via Upstage · zdr | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint upstage/zdr) | |
| OpenRouter未披露 | Z.ai: GLM 5.3 Flashvia Relace · fp4 | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token (endpoint relace/fp4) | |
| OpenRouter未披露 | Pareto Latest | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| OpenRouter未披露 | Z.ai: GLM Flash Latest | $0.03/百万缓存读 | input_cache_read: 0.00000003 / token | |
| Runware未披露 | Gemini 3.5 Flash-LitePer 1M | $0.03/百万缓存读 | $3e-8 / cachedInputToken | |
| Runware未披露 | GLM-5.3-FlashPer 1M | $0.03/百万缓存读 | $3e-8 / cachedInputToken | |
| Aiberm未披露 | Claude Sonnet 5 | $0.03/百万缓存读 | model_ratio 0.6522 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter第三方 | Meta: Muse Glimmer 30B (batch) | $0.032/百万缓存读 | input_cache_read: 0.000000032 / token (endpoint deepinfra/bf16) | |
| OpenRouter第三方 | OpenAI: gpt-oss-120bvia PrimeIntellect · fp4 | $0.032/百万缓存读 | input_cache_read: 0.000000032 / token (endpoint primeintellect/fp4) | |
| OpenRouter第三方 | Qwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4 | $0.033/百万缓存读 | input_cache_read: 0.0000000325 / token (endpoint darkbloom/fp4) | |
| OpenRouter第三方 | Tencent: Hy3peak 0000–1600 UTC · via Tencent · fp8 | $0.033/百万缓存读 | input_cache_read: 0.000000033 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouter未披露 | DeepSeek: DeepSeek V4 Flash Latest | $0.035/百万缓存读 | input_cache_read: 0.000000035 / token | |
| Runware未披露 | gpt-oss-safeguard-20bPer 1M | $0.035/百万缓存读 | $3.5e-8 / cachedInputToken | |
| OpenRouter官方 | Xiaomi: MiMo-V2.6-Pro-UltraSpeed | $0.036/百万缓存读 | input_cache_read: 0.000000036 / token (endpoint xiaomi/fp8) | |
| OpenRouter官方 | Google: Gemini 3.6 Flash (batch) | $0.038/百万缓存读 | input_audio_cache: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.6 Flash (batch) | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.7 Flash (batch) | $0.038/百万缓存读 | input_audio_cache: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.7 Flash (batch) | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.8 Flash (batch) | $0.038/百万缓存读 | input_audio_cache: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 3.8 Flash (batch) | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | OpenAI: GPT-4o-mini (batch) | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint openai) | |
| OpenRouter官方 | OpenAI: GPT-5.4 Mini (batch) | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint openai) | |
| OpenRouter第三方 | OpenAI: gpt-oss-safeguard-20b | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token | |
| OpenRouter第三方 | PrismML: Ternary Bonsai 2 27B | $0.038/百万缓存读 | input_cache_read: 0.0000000375 / token (endpoint darkbloom/int4) | |
| OpenRouter第三方 | Tencent: Hy4 previewoff-peak 1600–0000 UTC · via Tencent · fp8 | $0.038/百万缓存读 | input_cache_read: 0.0000000378 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| Aiberm未披露 | GPT-6 Sol | $0.039/百万缓存读 | model_ratio 0.5652 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| Aiberm未披露 | GPT-6.1 Sol | $0.039/百万缓存读 | model_ratio 0.5652 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| OpenRouter官方 | Qwen: Qwen3 Coder Flash | $0.039/百万缓存读 | input_cache_read: 0.000000039 / token (endpoint alibaba) | |
| Aiberm未披露 | Claude Opus 5.5 | $0.04/百万缓存读 | model_ratio 0.8688 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter官方 | KT: Mi:dm K 3.0 Pro | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint kt) | |
| OpenRouter官方 | LiquidAI: LFM2.5-2.6B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint liquid/fp8) | |
| OpenRouter第三方 | Meta: Muse Glimmer 30B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint deepinfra/bf16) | |
| OpenRouter官方 | Mistral: Devstral 2 2512 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token | |
| OpenRouter官方 | Mistral: Mistral Medium 3via Mistral · zdr | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint mistral/zdr) | |
| OpenRouter官方 | Mistral: Mistral Medium 3.1via Mistral · zdr | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint mistral/zdr) | |
| OpenRouter官方合作 | OpenAI: GPT-5.6 Luna提示词超过 272Kvia Amazon Bedrock · global | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouter官方合作 | OpenAI: GPT-5.6 Luna Pro提示词超过 272Kvia Azure | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>272000; endpoint azure) | |
| OpenRouter第三方 | PrismML: Ternary Bonsai 2 9B | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint darkbloom/int4) | |
| OpenRouter第三方 | Qwen: Qwen3.5-9Bvia Darkbloom · fp4 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint darkbloom/fp4) | |
| OpenRouter官方 | Qwen: Qwen3.7 Flash提示词超过 256Kvia Alibaba | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (>256000; endpoint alibaba) | |
| OpenRouter第三方 | Qwen: Qwen3.8 27B (batch) | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint deepinfra/bf16) | |
| OpenRouter第三方 | StepFun: Step 3.7 Flashvia Novita · fp8 | $0.04/百万缓存读 | input_cache_read: 0.00000004 / token (endpoint novita/fp8) | |
| Aiberm未披露 | Claude Haiku 4.5 | $0.04/百万缓存读 | model_ratio 0.875 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Haiku 4.5 Thinking | $0.04/百万缓存读 | model_ratio 0.875 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter第三方 | MiniMax: MiniMax M2.7via GMICloud · fp8 | $0.042/百万缓存读 | input_cache_read: 0.000000042 / token (endpoint gmicloud/fp8) | |
| OpenRouter第三方 | Tencent: Hy4 previewpeak 0000–1600 UTC · via Tencent · fp8 | $0.042/百万缓存读 | input_cache_read: 0.000000042 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouter第三方 | MiniMax: MiniMax M3 (batch) | $0.045/百万缓存读 | input_cache_read: 0.0000000448 / token (endpoint deepinfra/fp8) | |
| Aiberm未披露 | Claude Sonnet 4.5 20250929 | $0.045/百万缓存读 | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.5 20250929 Thinking | $0.045/百万缓存读 | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.6 | $0.045/百万缓存读 | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | Claude Sonnet 4.6 Thinking | $0.045/百万缓存读 | model_ratio 0.9775 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Runware未披露 | Shieldstral 1.0 3BPer 1M | $0.045/百万缓存读 | $4.5e-8 / cachedInputToken | |
| Aiberm未披露 | Gemini 4 Argon | $0.046/百万缓存读 | model_ratio 1 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| Aiberm未披露 | GPT-5.6 Terra | $0.049/百万缓存读 | model_ratio 0.7065 × $2/M · group default ×0.23 · cache_ratio 0.15 | |
| Aiberm未披露 | Claude Opus 5 | $0.05/百万缓存读 | model_ratio 1.086 × $2/M · group default ×0.23 · cache_ratio 0.1 | |
| OpenRouter官方 | Anthropic: Claude Haiku 4.5 (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint anthropic) | |
| OpenRouter官方合作 | Anthropic: Claude Haiku 5.5提示词超过 100Kvia Google · global | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (>100000; endpoint google-vertex/global) | |
| OpenRouter官方 | Anthropic: Claude Sonnet 5.5 (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint anthropic) | |
| OpenRouter官方 | Google: Gemini 3 Flash Previewvia Google AI Studio | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.1 Flash Litevia Google AI Studio | $0.05/百万缓存读 | input_audio_cache: 0.00000005 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 3.1 Flash Lite Previewvia Google AI Studio | $0.05/百万缓存读 | input_audio_cache: 0.00000005 / token (endpoint google-ai-studio) | |
| OpenRouter官方 | Google: Gemini 4 Argon (batch) | $0.05/百万缓存读 | input_audio_cache: 0.00000005 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 4 Argon (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 4 Carbon (batch) | $0.05/百万缓存读 | input_audio_cache: 0.00000005 / token (endpoint google-vertex/global) | |
| OpenRouter官方 | Google: Gemini 4 Carbon (batch) | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint google-vertex/global) | |
| OpenRouter第三方 | Google: Gemma 3 12Bvia NextBit · int4 | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint nextbit/int4) | |
| OpenRouter官方 | Inference.net: Schematron V2 Smallvia InferenceNet · bf16 | $0.05/百万缓存读 | input_cache_read: 0.00000005 / token (endpoint inference-net/bf16) |
