DeepSeekDeepSeekchatUnknown
DeepSeek V4 Flash
Canonical Model Slug: deepseek-v4-flash
Vision: YesTool Calling: YesReasoning: YesPrompt Caching: Yes
收錄報價總數12across 10 providers
可比較標準報價數12USD / 1M Token basis
最低 Input / 1M$0.03Standard tier min
最低 Output / 1M$0.18Standard tier min
最大 Context Window1,049,000Max tokens
Max Output Tokens1,048,576Completion limit
跨供應商 Input / Output 費率視覺化比較 (USD / 1M Tokens)
Showing top 12 comparable offerings sorted by input price
跨供應商價格比較表 (12)
所有價格均可追溯至 LiteLLM 或國網中心原始紀錄，國網報價固定置頂。勾選多列可鎖定圖表比較，點擊「原始紀錄」可檢視完整 JSON 欄位。
| Select | Marketplace · Underlying | Context Window | 計價方案 (Tier) · Region | 操作 | |||
|---|---|---|---|---|---|---|---|
OpenRouter openrouter/deepseek/deepseek-v4-flash | OpenRouter Marketplace Inference: Not Specified | $0.03 ★ 最低價 | $1.28 | 1,048,576 | StandardGlobal + Cache / Batch rates | ||
DeepInfra deepinfra/deepseek-ai/DeepSeek-V4-Flash | DeepInfra Serverless Inference: DeepInfra | $0.09 | $0.18 ★ 最低價 | 1,048,576 | StandardGlobal + Cache / Batch rates | ||
Fireworks AI fireworks_ai/accounts/fireworks/models/deepseek-v4-flash | Fireworks AI Inference: Fireworks AI | $0.14 | $0.28 | 1,048,576 | StandardGlobal + Cache / Batch rates | ||
Fireworks AI fireworks_ai/deepseek-v4-flash | Fireworks AI Inference: Fireworks AI | $0.14 | $0.28 | 1,048,576 | StandardGlobal + Cache / Batch rates | ||
Nebius AI Studio nebius/deepseek-ai/DeepSeek-V4-Flash | Nebius AI Studio Inference: Nebius | $0.14 | $0.28 | 1,048,576 | StandardGlobal | ||
TensorMesh tensormesh/deepseek-ai/DeepSeek-V4-Flash | TensorMesh Inference: TensorMesh | $0.14 | $0.28 | 32,768 | StandardGlobal + Cache / Batch rates | ||
Novita AI novita/deepseek/deepseek-v4-flash | Novita AI Inference: Novita AI | $0.14 | $0.28 | 1,048,576 | StandardGlobal + Cache / Batch rates | ||
Weights & Biases (Weave) wandb/deepseek-ai/DeepSeek-V4-Flash | W&B Inference Inference: Not Specified | $0.14 | $0.28 | 1,049,000 | StandardGlobal + Cache / Batch rates | ||
Azure AI Foundry azure_ai/deepseek-v4-flash | Microsoft Azure AI Inference: Microsoft Azure | $0.19 | $0.51 | 1,000,000 | StandardGlobal + Cache / Batch rates | ||
Alibaba DashScope dashscope/deepseek-v4-flash | Alibaba Cloud Inference: Alibaba Cloud | $0.20 | $0.40 | 1,000,000 | StandardGlobal + Cache / Batch rates | ||
DeepSeek deepseek-v4-flash | Direct / Official Inference: DeepSeek | $0.30 | $1.20 | 1,000,000 | StandardGlobal + Cache / Batch rates | ||
DeepSeek deepseek/deepseek-v4-flash | Direct / Official Inference: DeepSeek | $0.30 | $1.20 | 1,000,000 | StandardGlobal + Cache / Batch rates |
同系列獨立變體與不同參數規模模型（嚴格分離、不強制合併）
依據平台標準化規則，不同參數規模（如 20B 與 120B）、Safeguard 安全微調版、Preview 版與 GGUF 量化版本皆維持獨立比較，不混入上方報價表。
Fw DeepSeek V4 Pro
fw-deepseek-v4-pro
Unknown1 offerings
DeepSeek V4 Pro
deepseek-v4-pro
Unknown11 offerings
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731
Unknown14 offerings
DeepSeek Chat
deepseek-chat
Open Weight3 offerings
Qwencloud DeepSeek V4 Flash
qwencloud-deepseek-v4-flash
Open Weight1 offerings
Qwencloud DeepSeek V4 Flash 0731
qwencloud-deepseek-v4-flash-0731
Open Weight1 offerings
Qwencloud DeepSeek V4 Pro
qwencloud-deepseek-v4-pro
Open Weight1 offerings
Qwen_ai_platform DeepSeek V4 Flash
qwen_ai_platform-deepseek-v4-flash
Open Weight1 offerings