DeepSeek V4 Pro 0813 API Pricing
DeepSeek · Mid-tier · Apache 2.0 · released 2026-08. Prices in USD per 1 million tokens. Data snapshot: 2026-09-28.
The price we publish for DeepSeek V4 Pro 0813 has changed 20 times since 2026-08-15, most recently by +21.3% on 2026-09-28; it is now the 51st cheapest of 108 Mid-tier models. Buying from Ionstream rather than at the rate quoted here lowers the token price by about 53%. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.40 per 1M tokens
- Output: $4.20 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.40
- Context window: 1M
DeepSeek V4 Pro 0813 market position
On blended price ($3.06 per 1M tokens at 30% input, 70% output) it is cheaper than 53% of Mid-tier models: 51st cheapest of 108. Across every category it is cheaper than 31% of priced text models in the catalogue: 193rd cheapest of 281.
DeepSeek V4 Pro 0813 licence, size and capabilities
DeepSeek V4 Pro 0813 is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its parameter count is not published. Listed capabilities: Text, Reasoning, Code, Agents. Filling its 1M context window once costs $0.40 in input tokens at list price.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $270 |
| Knowledge Q&A | 2,000 / 800 | $416 |
| Meeting Summary | 10,000 / 1,200 | $903 – $904 |
| Marketing Content | 2,500 / 1,800 | $856 |
| Coding Task | 3,000 / 2,000 | $960 |
| Invoice Processing | 1,500 / 600 | $312 |
| Call Summary | 2,000 / 700 | $374 |
| Agent Workflow | 6,000 / 3,000 | $1.5K |
DeepSeek V4 Pro 0813 pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 22 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-28 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
Cheapest host: Ionstream at $0.23 input / $1.96 output per 1M tokens, 53% below the price we publish on a blended basis (30% input, 70% output). The dearest, Venice, charges 2.8x the cheapest.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Ionstream | $0.23 | $1.96 |
| Baidu — fp8 | $0.66 | $1.98 |
| StreamLake | $0.66 | $1.98 |
| DeepSeek | $0.66 | $1.98 |
| DeepInfra — fp8 | $1.30 | $2.60 |
| Phala | $0.96 | $2.88 |
| Novita — fp8 | $0.99 | $2.97 |
| NextBit — fp8 | $1.06 | $3.17 |
| GMICloud — fp8 | $1.06 | $3.17 |
| Relace — fp4 | $0.35 | $3.50 |
| Alibaba | $1.12 | $3.37 |
| Io Net — fp8 | $1.24 | $3.50 |
| Wafer (the price shown above) | $0.40 | $4.20 |
| Sail Research — fp4 | $0.40 | $4.30 |
| CoreWeave — fp8 | $1.31 | $3.96 |
| AtlasCloud — fp8 | $1.32 | $3.96 |
| Parasail — fp8 | $1.32 | $3.96 |
| Together | $1.32 | $3.96 |
| DigitalOcean | $1.32 | $3.96 |
| SiliconFlow — fp8 | $1.32 | $3.96 |
| Cloudflare | $1.32 | $3.96 |
| Venice | $1.65 | $4.95 |
DeepSeek V4 Pro 0813 price history
DeepSeek V4 Pro 0813 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.43 input / $0.87 output per 1M tokens. The price we publish has changed 20 times since then, 6 of them a change of reference host rather than a repricing. The latest change, on 2026-09-28, was +21.3% on the blended price (30% input, 70% output), to $0.40 input / $4.20 output. Net of all changes, the blended price is +313.8% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-09-28 | $0.24 / $3.50 | $0.40 / $4.20 | +21.3% |
| 2026-09-27 | $0.26 / $0.79 | $0.24 / $3.50 | +298.3% (reference host changed, not a repricing) |
| 2026-09-26 | $0.46 / $1.39 | $0.26 / $0.79 | -42.9% |
| 2026-09-24 | $0.50 / $1.50 | $0.46 / $1.39 | -7.4% |
| 2026-09-23 | $0.62 / $2.88 | $0.50 / $1.50 | -45.7% (reference host changed, not a repricing) |
15 earlier changes are not listed.
Alternatives to DeepSeek V4 Pro 0813
- Next cheaper Mid-tier model: Qwen3 Max (Alibaba) at $2.96 blended, 3% less.
- Next more expensive: Sakana Namazu (sakana) at $3.08 blended, 1% more.
Common questions about DeepSeek V4 Pro 0813 pricing
- How much does DeepSeek V4 Pro 0813 cost?
- DeepSeek V4 Pro 0813 costs $0.40 per million input tokens and $4.20 per million output tokens on the API.
- Does DeepSeek V4 Pro 0813 offer batch or cached pricing?
- Prompt-cache reads cost $0.40/M input tokens. No batch pricing is published.
- What would DeepSeek V4 Pro 0813 cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, DeepSeek V4 Pro 0813 costs about $270 at list prices.
- Has the price of DeepSeek V4 Pro 0813 changed?
- DeepSeek V4 Pro 0813 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.43 input / $0.87 output per 1M tokens. The price we publish has changed 20 times since then, 6 of them a change of reference host rather than a repricing. The latest change, on 2026-09-28, was +21.3% on the blended price (30% input, 70% output), to $0.40 input / $4.20 output. Net of all changes, the blended price is +313.8% against 2026-08-15.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for DeepSeek V4 Pro 0813 in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server