DeepSeek V4 Pro 0813 API pricing
DeepSeek · Mid-range price tier · MIT · released 2026-08. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
Outlier listing. The price we quote is one host's rate with input near free and output at or above the going rate, not what most hosts charge, so a cost built on it can be far from what you would pay. The typical host charges about $1.32 per 1M input tokens for this model.
A support ticket workload of 100K requests a month costs $238.65 on DeepSeek V4 Pro 0813; the next cheaper model in the Mid-range price tier for this workload, Gemini 3 Flash Preview, does it for $225.00. The price we quote for DeepSeek V4 Pro 0813 has changed 33 times since 2026-08-15, most recently by -4.7% on 2026-11-08; it is now the 49th cheapest of 113 models in the Mid-range price tier. Buying from DeepSeek rather than at the price we quote lowers the token price by about 50%. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.111 per 1M tokens
- Output: $4.44 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.097 per 1M tokens
- Context window: 1M tokens
- Arena ELO: 1445 as of 2026-11-08
Market position
On blended price ($3.1413 per 1M tokens at 30% input, 70% output) it is cheaper than 57% of models in the Mid-range price tier: 49th cheapest of 113. Across every price tier it is cheaper than 31% of priced text models in the catalogue: 209th cheapest of 303. Its Arena ELO of 1445 ranks 44th of the 160 models that carry one, tied with 2 others, above 72% of them. With an Arena score of 1445, DeepSeek V4 Pro 0813 clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
DeepSeek V4 Pro 0813 is open source: its weights are published under MIT, 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, Agents. Filling its 1M context window once costs $0.111 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 20 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: DeepSeek at $0.66 input / $1.98 output per 1M tokens, 50% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $198.00 there against $238.65 at the price we quote, a difference of $40.65 a month. The dearest, Relace, charges 3.6x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepSeek (model maker) | $0.66 | $1.98 | not declared |
| StreamLake | $0.66 | $1.98 | not declared |
| Sail Research | $1.35 | $2.40 | fp4 |
| DeepInfra | $1.30 | $2.60 | fp8 |
| Novita | $0.99 | $2.97 | fp8 |
| GMICloud | $1.056 | $3.168 | fp8 |
| Alibaba | $1.122 | $3.366 | not declared |
| Wafer | $0.285 | $4.30 | mxfp4 |
| Baidu | $1.3187 | $3.956 | fp8 |
| CoreWeave | $1.31 | $3.96 | fp8 |
| BaseTen | $1.32 | $3.96 | fp4 |
| AtlasCloud | $1.32 | $3.96 | fp8 |
| Nebius | $1.32 | $3.96 | fp8 |
| Parasail | $1.32 | $3.96 | fp8 |
| Together | $1.32 | $3.96 | not declared |
| DigitalOcean | $1.32 | $3.96 | not declared |
| SiliconFlow | $1.32 | $3.96 | fp8 |
| Cloudflare | $1.32 | $3.96 | not declared |
| Venice | $1.65 | $4.95 | not declared |
| Relace | $0.0999 | $8.00 | fp4 |
List prices as published on 2026-11-12, 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. These listings are promotional rates, below the host's standard rate: StreamLake's, 50% off; Novita's, 25% off; GMICloud's, 20% off; and Baidu's, 0% off.
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 DeepSeek 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 | $237 – $239 |
| Knowledge Q&A | 2,000 / 800 | $375 – $377 |
| Meeting Summary | 10,000 / 1,200 | $642 – $644 |
| Marketing Content | 2,500 / 1,800 | $826 – $827 |
| Coding Task | 3,000 / 2,000 | $919 – $921 |
| Invoice Processing | 1,500 / 600 | $282 – $283 |
| Call Summary | 2,000 / 700 | $333 |
| Agent Workflow | 6,000 / 3,000 | $1.4K |
Price history
DeepSeek V4 Pro 0813 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.435 input / $0.87 output per 1M tokens. The price we quote has changed 33 times since then, 11 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-08, was -4.7% on the blended price (30% input, 70% output), to $0.111 input / $4.44 output. Net of all changes, the blended price is +324.8% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-08 | $0.1165 / $4.66 | $0.111 / $4.44 | -4.7% |
| 2026-11-06 | $0.103 / $4.11 | $0.1165 / $4.66 | +13.4% |
| 2026-11-05 | $0.115 / $4.60 | $0.103 / $4.11 | -10.6% |
| 2026-11-04 | $0.115 / $4.00 | $0.115 / $4.60 | +14.8% |
| 2026-11-01 | $0.66 / $1.98 | $0.115 / $4.00 | +78.9% (quoted host changed, not a repricing) |
28 earlier changes are not listed.
Alternatives to DeepSeek V4 Pro 0813
3 of the 4 comparable models below cost less than DeepSeek V4 Pro 0813: Nemotron 3 Ultra undercuts it by 41%, at the same Arena score.
- Next cheaper model in the Mid-range price tier: Inkling (thinkingmachines) at $3.135 blended, under 1% less.
- Next more expensive: GLM 5 Turbo (Zhipu) at $3.16 blended, 1% more.
The nearest models in the Mid-range price tier on Arena ELO, each with its blended price and score difference against DeepSeek V4 Pro 0813.
- Nemotron 3 Ultra (Nvidia): $0.60 in / $2.40 out per 1M, Arena ELO 1445 (41% cheaper, same Arena ELO)
- Kimi K2.5 (Moonshot): $0.532 in / $3.325 out per 1M, Arena ELO 1445 (21% cheaper, same Arena ELO)
- GPT-6.1 Sol (OpenAI): $2.00 in / $10.00 out per 1M, Arena ELO 1446 (142% more expensive, 1 ELO point higher)
- GLM 5 (Zhipu): $1.00 in / $3.20 out per 1M, Arena ELO 1446 (19% cheaper, 1 ELO point higher)
- Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 97% cheaper, 11 ELO points lower, out of 39 models in that band.
- Highest Arena ELO within 20% of this price: Gemini 3.8 Flash (Google), 9% cheaper, 55 ELO points higher, out of 16 models in that price band.
DeepSeek V4 Pro 0813 head to head
Other models from DeepSeek
The 8 nearest to DeepSeek V4 Pro 0813 in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.
- DeepSeek V4.1 Flash 1017: $0.15 / $0.60
- DeepSeek V3: $0.32 / $0.89
- DeepSeek V3.1: $0.25 / $0.95
- DeepSeek V3.1 Terminus: $0.27 / $1.00
- DeepSeek V3 0324: $0.29 / $1.14
- DeepSeek V4 Flash Vision Exp: $0.44 / $1.32
- DeepSeek V4 Pro 0423: $0.9553 / $1.9105
- R1 0528: $0.50 / $2.15
All 14 DeepSeek models and prices
Common questions about DeepSeek V4 Pro 0813 pricing
- How much does DeepSeek V4 Pro 0813 cost?
- We quote DeepSeek V4 Pro 0813 at $0.111 per 1M input tokens and $4.44 per 1M output tokens. That figure matches none of the rates its 20 hosts list. The model maker, DeepSeek, lists it at $0.66 per 1M input tokens and $1.98 per 1M output tokens. Prices as listed on 2026-11-12.
- Which host is cheapest for DeepSeek V4 Pro 0813?
- Cheapest host: DeepSeek at $0.66 input / $1.98 output per 1M tokens, 50% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $198.00 there against $238.65 at the price we quote, a difference of $40.65 a month. The dearest, Relace, charges 3.6x the cheapest. Host rates as listed on 2026-11-12.
- Does DeepSeek V4 Pro 0813 offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.097 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would DeepSeek V4 Pro 0813 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $239 on DeepSeek V4 Pro 0813 at the list price quoted on 2026-11-12.
- Can DeepSeek V4 Pro 0813 be self-hosted?
- Yes. DeepSeek V4 Pro 0813 is open source: its weights are published under MIT, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- 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 $0.435 input / $0.87 output per 1M tokens. The price we quote has changed 33 times since then, 11 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-08, was -4.7% on the blended price (30% input, 70% output), to $0.111 input / $4.44 output. Net of all changes, the blended price is +324.8% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server