4,604 个模型 · 10,135 个价格 · 最近采集 21 分钟前 · 30 天内 383 条需关注的调价
每个平台公布的每一个价格
采集器定时读取 7 个平台公开的全部价格（默认每天一次），并保存读到的原始页面。没有任何手工录入。搜索一个模型，就能看到现在按单位谁最便宜。
Claude 
Gemini 
DeepSeek 
MiniMax 
GLM 
Kimi 
Mistral 第 1–52 条，共 52 条
每百万缓存读取 token52
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Runware未披露 | Claude Haiku 5.5≤ 100K context | $0.01/百万缓存读最低 | $1e-8 / cachedInputToken · ≤ 100K context | |
| Runware未披露 | DeepSeek-V4.1-FlashPer 1M | $0.01/百万缓存读最低 | $1e-8 / cachedInputToken | |
| Runware未披露 | DeepSeek-V4.1-Flash-1017Per 1M | $0.01/百万缓存读最低 | $1e-8 / cachedInputToken | |
| Runware未披露 | GPT-6 Luna≤ 272K context | $0.01/百万缓存读最低 | $1e-8 / cachedInputToken · ≤ 272K context | |
| Runware未披露 | Gemma 4 31BPer 1M | $0.012/百万缓存读 | $1.2e-8 / cachedInputToken | |
| Runware未披露 | DeepSeek-V4-Flash-0731Per 1M | $0.014/百万缓存读 | $1.4e-8 / cachedInputToken | |
| Runware未披露 | MiniMax M3.1 FlashPer 1M | $0.015/百万缓存读 | $1.5e-8 / cachedInputToken | |
| Runware未披露 | GPT-5.6 LunaPer 1M | $0.02/百万缓存读 | $2e-8 / cachedInputToken | |
| Runware未披露 | GPT-6 Luna> 272K context | $0.02/百万缓存读 | $2e-8 / cachedInputToken · > 272K context | |
| 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 | |
| Runware未披露 | gpt-oss-safeguard-20bPer 1M | $0.035/百万缓存读 | $3.5e-8 / cachedInputToken | |
| Runware未披露 | Shieldstral 1.0 3BPer 1M | $0.045/百万缓存读 | $4.5e-8 / cachedInputToken | |
| 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 | |
| Runware未披露 | MiniMax M3≤ 512K context | $0.06/百万缓存读 | $6e-8 / cachedInputToken · ≤ 512K context | |
| 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 | |
| Runware未披露 | DeepSeek-V4-Pro-0813Per 1M | $0.079/百万缓存读 | $7.9e-8 / cachedInputToken | |
| Runware未披露 | Claude Haiku 4.5Per 1M | $0.1/百万缓存读 | $1e-7 / cachedInputToken | |
| Runware未披露 | Gemini 4 ArgonThrough Nov 30 · 2026 | $0.1/百万缓存读 | $1e-7 / cachedInputToken · Through Nov 30, 2026 | |
| Runware未披露 | GPT-6.1 Sol≤ 272K context | $0.1/百万缓存读 | $1e-7 / cachedInputToken · ≤ 272K context | |
| Runware未披露 | GPT-6.1 Terra> 272K context | $0.1/百万缓存读 | $1e-7 / cachedInputToken · > 272K context | |
| Runware未披露 | MiniMax M3> 512K context | $0.12/百万缓存读 | $1.2e-7 / cachedInputToken · > 512K context | |
| Runware未披露 | Gemini 3.5 FlashPer 1M | $0.15/百万缓存读 | $1.5e-7 / cachedInputToken | |
| Runware未披露 | Gemini 3.6 FlashPer 1M | $0.15/百万缓存读 | $1.5e-7 / cachedInputToken | |
| Runware未披露 | GLM-5.2Per 1M | $0.16/百万缓存读 | $1.6e-7 / cachedInputToken | |
| 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 | |
| Runware未披露 | Claude Fable 5.1Per 1M | $0.25/百万缓存读 | $2.5e-7 / cachedInputToken | |
| 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 | |
| Runware未披露 | GPT-5.6 SolPer 1M | $0.4/百万缓存读 | $4.0000000000000003e-7 / cachedInputToken | |
| Runware未披露 | GPT-6 Sol> 272K context | $0.4/百万缓存读 | $4e-7 / cachedInputToken · > 272K context | |
| Runware未披露 | Claude Opus 4.7Per 1M | $0.5/百万缓存读 | $5e-7 / cachedInputToken | |
| Runware未披露 | Claude Opus 4.8Per 1M | $0.5/百万缓存读 | $5e-7 / cachedInputToken | |
| Runware未披露 | Claude Opus 5Per 1M | $0.5/百万缓存读 | $5e-7 / cachedInputToken | |
| Runware未披露 | GPT-5.5Per 1M | $0.5/百万缓存读 | $5e-7 / cachedInputToken | |
| Runware未披露 | Grok 4.7< 200K context | $0.5/百万缓存读 | $5e-7 / cachedInputToken · < 200K context | |
| Runware未披露 | Claude Fable 5Per 1M | $1/百万缓存读 | $0.000001 / cachedInputToken | |
| Runware未披露 | GPT-6 Astra≤ 272K context | $1/百万缓存读 | $0.000001 / cachedInputToken · ≤ 272K context | |
| Runware未披露 | Grok 4.7≥ 200K context | $1/百万缓存读 | $0.000001 / cachedInputToken · ≥ 200K context | |
| Runware未披露 | GPT-6 Astra> 272K context | $2/百万缓存读 | $0.000002 / cachedInputToken · > 272K context |
