DeepSeek V4 Pro
deepseek/v4-pro出品方： DeepSeek · 系列: deepseek-thinking · 发布 2026-04-24 · 知识截止: 2025-05
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
能力清单
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding100
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output97
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume17/20
Cost efficiency65
- Headline price (log-scaled)60/95
- Has prompt-cache pricing5/5
Long context90
- Context window (100K → 2M)80/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $2.61 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $5.22 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.30 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $4.35 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $5.74 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
定价详情
推荐定价来自 deepseek · deepseek-v4-pro
最便宜的渠道： sensenova · Unknown 输入 + Unknown 输出
在 72 家渠道可用
| 服务商 | 服务商模型 ID | 输入 / 1M | 输出 / 1M | 上下文 | 发布日期 |
|---|---|---|---|---|---|
| DeepSeek deepseek | deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-08-12 |
| Azure azure | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| OpenRouter openrouter | deepseek/deepseek-v4-pro | $0.955 | $1.91 | 1.05M | 2026-04-24 |
| Vercel AI Gateway vercel | deepseek/deepseek-v4-pro | $0.660 | $1.98 | 1M | 2026-04-24 |
| Together AI togetherai | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 512K | 2026-04-24 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-V4-Pro | $1.30 | $2.60 | 1.05M | 2026-04-24 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-V4-Pro | $0.435 | $0.870 | 1.05M | 2026-04-24 |
| EmpirioLabs AI empiriolabs | deepseek-v4-pro | $1.65 | $3.30 | 1M | 2026-04-24 |
| SenseNova (China) sensenova | deepseek-v4-pro | Unknown | Unknown | 1.05M | 2026-08-12 |
| Alibaba Token Plan alibaba-token-plan | deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| NanoGPT nano-gpt | deepseek/deepseek-v4-pro | $1.10 | $2.20 | 1.05M | 2026-04-24 |
| CrofAI crof | deepseek-v4-pro | $0.350 | $0.800 | 1M | 2026-04-24 |
| Baseten baseten | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| CoreWeave wandb | deepseek-ai/DeepSeek-V4-Pro | $1.15 | $2.55 | 1.05M | 2026-04-24 |
| SiliconFlow siliconflow | deepseek-ai/DeepSeek-V4-Pro | $1.50 | $3.13 | 1M | 2026-04-24 |
| LLM Gateway llmgateway-providers | deepinfra/deepseek-v4-pro | $1.30 | $2.60 | 1.05M | 2026-04-24 |
| LLM Gateway llmgateway-providers | deepseek/deepseek-v4-pro | $0.435 | $0.870 | 1.05M | 2026-04-24 |
| LLM Gateway llmgateway-providers | runware/deepseek-v4-pro | $0.961 | $1.92 | 1.05M | 2026-04-24 |
| LLM Gateway llmgateway-providers | tencent/deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| LLM Gateway llmgateway-providers | canopywave/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| LLM Gateway llmgateway-providers | fireworks/deepseek-v4-pro | $1.32 | $3.96 | 1.05M | 2026-04-24 |
| LLM Gateway llmgateway-providers | together-ai/deepseek-v4-pro | $1.32 | $3.96 | 1.05M | 2026-04-24 |
| above.dev above | deepseek-v4-pro | $0.726 | $2.18 | 1M | 2026-08-12 |
| Kilo Gateway kilo | deepseek/deepseek-v4-pro | $1.60 | $3.20 | 1.02M | 2026-04-24 |
| Venice AI venice | deepseek-v4-pro | $1.65 | $3.30 | 1M | 2026-04-24 |
| Alibaba Token Plan (China) alibaba-token-plan-cn | deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| Abacus abacus | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| NovitaAI novita-ai | deepseek/deepseek-v4-pro | $1.60 | $3.20 | 1.05M | 2026-04-24 |
| ClinePass cline-pass | cline-pass/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| routing.run routing-run | deepseek-v4-pro | $0.348 | $0.696 | 1M | 2026-04-24 |
| Neuralwatt neuralwatt | deepseek-v4-pro | $1.00 | $3.00 | 1.05M | 2026-04-24 |
| Auriko auriko | deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| ZenMux zenmux | deepseek/deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| UnoRouter unorouter | deepseek-v4-pro | $0.900 | $1.80 | 1M | 2026-04-24 |
| SiliconFlow (China) siliconflow-cn | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| Impossibl impossibl | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| GMI Cloud gmicloud | deepseek-ai/DeepSeek-V4-Pro | $1.39 | $2.78 | 1.05M | 2026-04-24 |
| Cloudflare AI Gateway cloudflare-ai-gateway | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 131K | 2026-04-24 |
| ai& aiand | deepseek-ai/deepseek-v4-pro | $1.00 | $2.50 | 1.05M | 2026-04-24 |
| FrogBot frogbot | deepseek-v4-pro | $1.74 | $3.48 | 128K | 2026-04-24 |
| AnyAPI anyapi | deepseek/deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| Volcengine Ark Coding Plan volcengine-coding-plan | deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| Ollama Cloud ollama-cloud | deepseek-v4-pro | $0.660 | $1.98 | 1.05M | 2026-04-24 |
| Model Oracle AI model-oracle-ai | deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| Nebius Token Factory nebius | deepseek-ai/DeepSeek-V4-Pro | $1.75 | $3.50 | 1.05M | 2026-04-24 |
| EBCloud ebcloud | DeepSeek-V4-Pro | $0.429 | $0.857 | 1M | 2026-04-24 |
| Charm Hyper hyper | deepseek-v4-pro | $2.40 | $4.80 | 1M | 2026-07-06 |
| Jalapeno Cloud jalapeno | DeepSeek-V4-Pro | $1.60 | $3.38 | 1.05M | 2026-04-24 |
| FastRouter fastrouter | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| OrcaRouter orcarouter | deepseek/deepseek-v4-pro | $0.442 | $0.884 | 1M | 2026-04-24 |
| SCNet Token Plan scnet-token-plan | DeepSeek-V4-Pro | Unknown | Unknown | 1M | 2026-04-24 |
| Ofox ofox | deepseek/deepseek-v4-pro | $1.32 | $3.96 | 1M | 2026-04-24 |
| Merge Gateway merge-gateway | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| Opper opper | deepseek-v4-pro | $1.79 | $3.58 | 1M | 2026-04-24 |
| Nvidia nvidia | deepseek-ai/deepseek-v4-pro | $0.435 | $0.870 | 1.05M | 2026-04-24 |
| Pioneer pioneer | deepseek-ai/DeepSeek-V4-Pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| OpenCode Go opencode-go | deepseek-v4-pro | $0.660 | $1.98 | 1M | 2026-04-24 |
| TensorX tensorx | deepseek/deepseek-v4-pro | $1.75 | $3.50 | 1.05M | 2026-04-24 |
| Eden AI edenai | deepseek/deepseek-v4-pro | $0.660 | $1.98 | 1M | 2026-04-24 |
| HPC-AI hpc-ai | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1.00M | 2026-04-24 |
| Modelis modelis | deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| OpenCode Zen opencode | deepseek-v4-pro | $1.74 | $3.84 | 1M | 2026-04-24 |
| Kenari kenari | deepseek-v4-pro | Unknown | Unknown | 1M | 2026-04-24 |
| Requesty requesty | deepseek-v4-pro | $1.32 | $3.96 | 1M | 2026-04-24 |
| DevPass (LLM Gateway) llmgateway | deepseek-v4-pro | $0.435 | $0.870 | 1.05M | 2026-04-24 |
| Vivgrid vivgrid | deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| TokenGo tokengo | deepseek/deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
| Cortecs cortecs | deepseek-v4-pro | $1.70 | $3.40 | 1.05M | 2026-04-24 |
| CrossModel crossmodel | deepseek/deepseek-v4-pro | $1.22 | $3.65 | 1M | 2026-04-24 |
| Arcee arcee | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 512K | 2026-04-24 |
| DigitalOcean digitalocean | deepseek-v4-pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| Alibaba (China) alibaba-cn | deepseek-v4-pro | $0.435 | $0.870 | 1M | 2026-04-24 |
各渠道数据存在不一致
- context_window varies: 1000000, 1002000, 1024000, 1048560, 1048576, 1049000, 1050000, 128000, 131072, 512000
- release_date varies (span 110d): 2026-04-24, 2026-07-06, 2026-08-12
各服务商对此模型的报告值存在差异。上方「核心数据」使用代表性服务商的值；逐项请以下表为准。
Frequently asked questions
How much does DeepSeek V4 Pro cost?
DeepSeek V4 Pro costs $0.435 per 1M input tokens and $0.870 per 1M output tokens, sourced from deepseek. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek V4 Pro?
DeepSeek V4 Pro has a context window of 1M tokens, with a max output of 393K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek V4 Pro support tool calling?
Yes. DeepSeek V4 Pro supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does DeepSeek V4 Pro support structured output / JSON mode?
Yes. DeepSeek V4 Pro supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can DeepSeek V4 Pro accept image input?
No. DeepSeek V4 Pro only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek V4 Pro open-weight?
Yes. DeepSeek V4 Pro's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek V4 Pro?
If DeepSeek V4 Pro doesn't fit, consider DeepSeek V4 Flash, DeepSeek V4.1 Flash, DeepSeek V4 Flash 0731. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek V4 Flash$0.15 in / $0.60 out
- DeepSeek V4.1 Flash$0.14 in / $0.28 out
- DeepSeek V4 Flash 0731$0.04 in / $0.07 out
- DeepSeek V4 Pro 0813$0.35 in / $0.80 out
- DeepSeek-V3.2$0.18 in / $0.35 out
Capability lists this model is in
最近更新：
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.