DeepSeek V4 Pro
API models and prices · 1
Usage-based billing: text rates are usually per million tokens; other units and tiers are stated per entry. Compare only the same currency, unit and billing conditions. Unverified cache pricing does not mean free.
DeepSeek V4 Pro
Pricing Not Public
Endpoint billing is unverified; excluded from lowest-cost comparisons.
Type / status: llm / documented_api
Use cases: Model price comparison, pay-as-you-go API selection, cross-provider call cost comparison
Excluded from default production recommendations; check model availability, pricing and usage conditions.
No single official DeepSeek token price: this base model is sold by several providers at different rates. Compare the reviewed channel offers for the actual per-provider price, currency and conditions.
Official model ID: deepseek-v4-pro
Model developer: DeepSeek · Service provider: DeepSeek · Market: com
Model family: DeepSeek · Model catalog only; see service-channel quotes
Canonical model entity with no single official token price; DeepSeek publishes this base model and the actual call price, currency and conditions live on each channel offer.
Documented API context: 262,000 tokens
Official source · Last verified: 2026-11-01T00:00:00.000Z
Capabilities and usage limits
Canonical model entity with no single official token price; DeepSeek publishes this base model and the actual call price, currency and conditions live on each channel offer.
Service channels / prices and conditions 5
Confirmed token quotes use USD / 1M tokens. Other billing units remain available at the source. Each channel retains its own price verification status; catalog retrieval dates are not price verification dates.
Ollama Cloud Model developer
Region: Global listing · Usage-based API · Metered billing · USD
Input $1.32 / 1M tokens · Output $3.96 / 1M tokens · Cached read $0.044 · Cached write Not disclosed
deepseek-v4-pro · DeepSeek V4 Pro / deepseek-v4-pro / deepseek-v4-pro
Ollama Cloud bills per token and requires purchased usage credits; concurrency is 3 (Pay as you go and Pro) or 10 (Max and Team). Off-peak rates (outside 12:00–18:00 UTC on weekdays and all weekend) are published separately by Ollama and are not folded into the standard rate shown here.
Cache billed separately
Channel context / maximum output: Unverified / Unverified tokens
Data use: Ollama states prompts and responses are never logged or trained on; models and compute are hosted primarily with NVIDIA Cloud Providers under no-logging, no-training and zero-retention requirements.
API: https://ollama.com/v1 · openai-compatible · api_key
Tools: Supported · Image input: Unverified
First-party price verified · 2026-11-01T00:00:00.000Z
Cloudflare Workers AI Model developer
Region: Global listing · Usage-based API · Metered billing · USD
Input $1.32 / 1M tokens · Output $3.96 / 1M tokens · Cached read $0.044 · Cached write Not disclosed
@cf/deepseek-ai/deepseek-v4-pro-0813 · DeepSeek V4 Pro 0813 / @cf/deepseek-ai/deepseek-v4-pro-0813 / deepseek-v4-pro
Workers AI bills in Neurons at $0.011 per 1,000 Neurons with a 10,000 Neurons per day free allocation on both the Free and Paid Workers plans; usage beyond that requires Workers Paid. Cloudflare publishes an equivalent token price (360000 neurons per M output tokens for this model), recorded here from the official token column so providers stay comparable; the Neuron unit itself is never converted for ranking.
Cache billed separately
Channel context / maximum output: Unverified / Unverified tokens
API: https://api.cloudflare.com/client/v4/accounts/%3Caccount%3E/ai/v1 · openai-compatible · api_key
Tools: Supported · Image input: Unverified
First-party price verified · 2026-11-01T00:00:00.000Z
DigitalOcean Inference Model developer
Region: Global listing · Usage-based API · Metered billing · USD
Input $1.32 / 1M tokens · Output $3.96 / 1M tokens · Cached read $0.044 · Cached write Not disclosed
deepseek-v4-pro-0813 · DeepSeek V4 Pro 0813 / deepseek-v4-pro-0813 / deepseek-v4-pro
DigitalOcean-hosted model rates. Serverless inference is prepaid only: promotional credits or a positive prepaid balance are required and access is suspended when both run out. Commercial Anthropic and OpenAI models billed by the original provider when using your own API keys. Batch inference discounts OpenAI and Anthropic models by up to 50%. Dedicated inference is billed per GPU-hour (for example H100 at $4.41/hour) and is not a model API price.
Cache billed separately
Channel context / maximum output: Unverified / Unverified tokens
API: https://inference.do-ai.run/v1 · openai-compatible · api_key
Tools: Supported · Image input: Unverified
First-party price verified · 2026-11-01T00:00:00.000Z
Microsoft Foundry Model developer
Region: Global listing · Usage-based API · Metered billing · USD
Input $1.74 / 1M tokens · Output $3.48 / 1M tokens · Cached read $0.145 · Cached write Not disclosed
foundry:global:deepseek-v4-pro · DeepSeek V4 Pro / foundry:global:deepseek-v4-pro / deepseek-v4-pro
Global deployment routed by Azure worldwide; the price is region-independent across the commercial regions checked. Pay-as-you-go token rates taken from the Azure Retail Prices API, which publishes some meters per 1K tokens; all figures here are normalized to per 1M tokens. Provisioned (PTU) reserved throughput, the Batch API and Priority/Flex processing modes are priced separately and are not listed.
Cache billed separately
Channel context / maximum output: Unverified / Unverified tokens
Tools: Supported · Image input: Unverified
First-party price verified · 2026-11-01T00:00:00.000Z
Microsoft Foundry Model developer
Region: Global listing · Usage-based API · Metered billing · USD
Input $1.91 / 1M tokens · Output $3.83 / 1M tokens · Cached read $0.16 · Cached write Not disclosed
foundry:data_zone:deepseek-v4-pro · DeepSeek V4 Pro / foundry:data_zone:deepseek-v4-pro / deepseek-v4-pro
Data Zone deployment pinned to a geographic data zone (EU or US) and priced separately from Global. Pay-as-you-go token rates taken from the Azure Retail Prices API, which publishes some meters per 1K tokens; all figures here are normalized to per 1M tokens. Provisioned (PTU) reserved throughput, the Batch API and Priority/Flex processing modes are priced separately and are not listed.
Cache billed separately
Channel context / maximum output: Unverified / Unverified tokens
Tools: Supported · Image input: Unverified
First-party price verified · 2026-11-01T00:00:00.000Z
Input means uncached tokens; cache read and write are added separately. Context tiers require the context size of each request, not monthly totals. Estimates exclude reasoning, audio and unconfirmed charges; top-ups are account funding, not additional token consumption.
服务渠道 / 价格与条件 5
中英文报价均使用美元 / 百万 tokens。各渠道分别保留来源和价格核验状态；目录抓取时间不等于价格核验时间。
Ollama Cloud 原厂
地区：国际区 · 按量 API · 按量计费 · USD
输入 $1.32 / 1M tokens · 输出 $3.96 / 1M tokens · 缓存读 $0.044 · 缓存写 未公布
deepseek-v4-pro · DeepSeek V4 Pro / deepseek-v4-pro / deepseek-v4-pro
Ollama Cloud 按 token 计费，需先购买 usage credits；并发上限 3（Pro/Pay as you go）或 10（Max/Team）。Off-peak rates (outside 12:00–18:00 UTC on weekdays and all weekend) are published separately by Ollama and are not folded into the standard rate shown here.
缓存可能另计
此渠道上下文 / 最大输出：待核验 / 待核验 tokens
数据使用：Ollama 官方声明提示与回复内容不记录、不用于训练；模型与算力主要由 NVIDIA Cloud Providers 托管，要求不记录、不训练、零保留。
API: https://ollama.com/v1 · openai-compatible · api_key
工具调用: 支持 · 图像输入: 待核实
一手价格已核对 · 2026-11-01T00:00:00.000Z
Cloudflare Workers AI 原厂
地区：国际区 · 按量 API · 按量计费 · USD
输入 $1.32 / 1M tokens · 输出 $3.96 / 1M tokens · 缓存读 $0.044 · 缓存写 未公布
@cf/deepseek-ai/deepseek-v4-pro-0813 · DeepSeek V4 Pro 0813 / @cf/deepseek-ai/deepseek-v4-pro-0813 / deepseek-v4-pro
Workers AI 按 Neurons 计费：$0.011 / 1,000 Neurons，免费额度为每日 10,000 Neurons（Free 与 Paid 计划均有），超出需 Workers Paid。官方同时公布 token 等价价（本模型 360000 neurons per M output tokens），此处按官方 token 列记录以便跨供应商比较，Neurons 单位不参与换算排序。
缓存可能另计
此渠道上下文 / 最大输出：待核验 / 待核验 tokens
API: https://api.cloudflare.com/client/v4/accounts/%3Caccount%3E/ai/v1 · openai-compatible · api_key
工具调用: 支持 · 图像输入: 待核实
一手价格已核对 · 2026-11-01T00:00:00.000Z
DigitalOcean Inference 原厂
地区：国际区 · 按量 API · 按量计费 · USD
输入 $1.32 / 1M tokens · 输出 $3.96 / 1M tokens · 缓存读 $0.044 · 缓存写 未公布
deepseek-v4-pro-0813 · DeepSeek V4 Pro 0813 / deepseek-v4-pro-0813 / deepseek-v4-pro
DigitalOcean 自营托管模型价格。Serverless inference 仅支持预付：需促销 credits 或正数预付余额，用尽后暂停访问。Anthropic / OpenAI 等商业模型在使用自带 API Key 时由原厂直接计费。Batch inference 对 OpenAI 与 Anthropic 模型最高 5 折。Dedicated inference 按 GPU 小时另计（如 H100 $4.41/小时），不是模型 API 价格。
缓存可能另计
此渠道上下文 / 最大输出：待核验 / 待核验 tokens
API: https://inference.do-ai.run/v1 · openai-compatible · api_key
工具调用: 支持 · 图像输入: 待核实
一手价格已核对 · 2026-11-01T00:00:00.000Z
Microsoft Foundry 原厂
地区：国际区 · 按量 API · 按量计费 · USD
输入 $1.74 / 1M tokens · 输出 $3.48 / 1M tokens · 缓存读 $0.145 · 缓存写 未公布
foundry:global:deepseek-v4-pro · DeepSeek V4 Pro / foundry:global:deepseek-v4-pro / deepseek-v4-pro
Global 部署：Azure 全球路由，价格不随区域变化（已核对多个商业区域一致）。价格为按量 token 单价，取自 Azure Retail Prices API；该 API 对部分计费项以 1K tokens 为单位发布，此处统一折算为每 1M tokens。Provisioned（PTU）预留吞吐、Batch API 与 Priority/Flex 处理模式另有计价，不在此列。
缓存可能另计
此渠道上下文 / 最大输出：待核验 / 待核验 tokens
工具调用: 支持 · 图像输入: 待核实
一手价格已核对 · 2026-11-01T00:00:00.000Z
Microsoft Foundry 原厂
地区：国际区 · 按量 API · 按量计费 · USD
输入 $1.91 / 1M tokens · 输出 $3.83 / 1M tokens · 缓存读 $0.16 · 缓存写 未公布
foundry:data_zone:deepseek-v4-pro · DeepSeek V4 Pro / foundry:data_zone:deepseek-v4-pro / deepseek-v4-pro
Data Zone 部署：限定地理数据区（EU 或 US），与 Global 分开计价。价格为按量 token 单价，取自 Azure Retail Prices API；该 API 对部分计费项以 1K tokens 为单位发布，此处统一折算为每 1M tokens。Provisioned（PTU）预留吞吐、Batch API 与 Priority/Flex 处理模式另有计价，不在此列。
缓存可能另计
此渠道上下文 / 最大输出：待核验 / 待核验 tokens
工具调用: 支持 · 图像输入: 待核实
一手价格已核对 · 2026-11-01T00:00:00.000Z
输入仅指未缓存 Tokens，缓存读写分别计入；上下文阶梯使用单次请求上下文，不是月累计用量。估算不含推理、音频和未确认的附加费用；充值属于账户资金，不重复算作 Token 消费。