DeepSeek V4 Pro 0423 API pricing

DeepSeek · Budget price tier · MIT · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-21.

A support ticket workload of 100K requests a month costs $210.00 on DeepSeek V4 Pro 0423; the next cheaper model in the Budget price tier for this workload, Aion-2.0, does it for $200.00. The price we quote for DeepSeek V4 Pro 0423 has changed 43 times since 2026-08-17, most recently on 2026-11-14 when the quoted host changed (-18.7%); it is now the 148th cheapest of 160 models in the Budget price tier. Buying from Baidu rather than at the price we quote lowers the token price by about 15%, for a quantized fp8 build. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.

Market position

On blended price ($1.32 per 1M tokens at 30% input, 70% output) it is cheaper than 8% of models in the Budget price tier: 148th cheapest of 160. Across every price tier it is cheaper than 52% of priced text models in the catalogue: 148th cheapest of 308. Its Arena ELO of 1451 ranks 36th of the 157 models that carry one, tied with 3 others, above 76% of them. With an Arena score of 1451, DeepSeek V4 Pro 0423 clears OptimNow's Standard working quality threshold: Standard (Arena 1419+), used for meeting summary, invoice processing and call summary. It is 18 points under the Strong bar (Arena 1469+), within the benchmark's 20-point noise. Each threshold is a distance below the best ranked model, which scores 1529 on Arena scores as of 11 Nov 2026.

Licence, size and capabilities

DeepSeek V4 Pro 0423 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 published size is 1.6T parameters. Listed capabilities: Text, Reasoning, Agents. Filling its 1M context window once costs $0.90 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 10 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: Baidu at $0.6608 input / $1.3216 output per 1M tokens, 15% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $165.20 there against $210.00 at the price we quote, a difference of $44.80 a month. The dearest, Azure, charges 2.9x the cheapest.

HostInput $/1MOutput $/1MPrecision
Baidu$0.6608$1.3216fp8
StreamLake$0.6622$1.3245fp8
Relace (price we quote)$0.90$1.50fp4
SiliconFlow$0.90$1.70fp8
DigitalOcean$1.044$2.088not declared
Novita$1.28$2.56fp8
DeepInfra$1.30$2.60fp8
Alibaba$1.416$2.832fp8
Venice$1.65$3.301not declared
Azure$1.91$3.83not declared

List prices as published on 2026-11-21, 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: Baidu's, 61% off; StreamLake's, 62% off; and Novita's, 20% 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 caseTokens (in/out)Monthly (after discounts – list)
Support Ticket1,500 / 500$147 – $210
Knowledge Q&A2,000 / 800$202 – $300
Meeting Summary10,000 / 1,200$1.0K – $1.1K
Marketing Content2,500 / 1,800$460 – $495
Coding Task3,000 / 2,000$465 – $570
Invoice Processing1,500 / 600$194 – $225
Call Summary2,000 / 700$271 – $285
Agent Workflow6,000 / 3,000$696 – $990

Price history

DeepSeek V4 Pro 0423 entered our daily price archive on 2026-08-17; tracking began on 2026-08-15. It listed at $1.32 input / $3.96 output per 1M tokens that day. The price we quote has changed 43 times since then, 9 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-14, was -18.7% on the blended price (30% input, 70% output), to $0.90 input / $1.50 output (quoted host changed, not a repricing). Net of all changes, the blended price is -58.3% against 2026-08-17.

Price chart for DeepSeek V4 Pro 0423: the blended price we quote went from $3.168 on 2026-08-17 to $1.32, across 43 changes.Price we quoteRange across hostsQuoted host changed$0$2.5$5$7.5$1017 Aug10 Sep4 Oct28 Oct21 Nov
Blended price per 1M tokens (30% input, 70% output). The grey band runs from the cheapest to the dearest host each day, quantized builds included, recorded from 30 Aug. Of the 84 days the range covers, the price we quote was the cheapest host's rate on 35.
DateOld price (in / out)New price (in / out)Blended change
2026-11-14$0.9553 / $1.9105$0.90 / $1.50-18.7% (quoted host changed, not a repricing)
2026-11-10$0.894 / $1.788$0.9553 / $1.9105+6.9%
2026-11-09$0.2617 / $0.5234$0.894 / $1.788+241.6%
2026-11-08$0.9553 / $1.9105$0.2617 / $0.5234-72.6%
2026-11-06$1.60 / $3.20$0.9553 / $1.9105-40.3% (quoted host changed, not a repricing)

38 earlier changes are not listed.

Alternatives to DeepSeek V4 Pro 0423

4 of the 4 comparable models below cost less than DeepSeek V4 Pro 0423: MiMo-V2.6-Flash undercuts it by 82%, at the same Arena score.

The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against DeepSeek V4 Pro 0423.

Other models from DeepSeek

The 8 nearest to DeepSeek V4 Pro 0423 in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.

All 14 DeepSeek models and prices

Common questions about DeepSeek V4 Pro 0423 pricing

How much does DeepSeek V4 Pro 0423 cost?
DeepSeek V4 Pro 0423 costs $0.90 per 1M input tokens and $1.50 per 1M output tokens at Relace, the host whose rate we quote. Relace serves a quantized fp4 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-21.
Which host is cheapest for DeepSeek V4 Pro 0423?
Cheapest host: Baidu at $0.6608 input / $1.3216 output per 1M tokens, 15% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $165.20 there against $210.00 at the price we quote, a difference of $44.80 a month. The dearest, Azure, charges 2.9x the cheapest. Host rates as listed on 2026-11-21.
Does DeepSeek V4 Pro 0423 offer batch or cached pricing?
Yes, for prompt caching only. Cache reads cost $0.20 per 1M tokens, as listed on 2026-11-21. No batch pricing is published.
What would DeepSeek V4 Pro 0423 cost per month?
With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $210 on DeepSeek V4 Pro 0423 at the list price quoted on 2026-11-21.
Can DeepSeek V4 Pro 0423 be self-hosted?
Yes. DeepSeek V4 Pro 0423 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 0423 changed?
DeepSeek V4 Pro 0423 entered our daily price archive on 2026-08-17; tracking began on 2026-08-15. It listed at $1.32 input / $3.96 output per 1M tokens that day. The price we quote has changed 43 times since then, 9 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-14, was -18.7% on the blended price (30% input, 70% output), to $0.90 input / $1.50 output (quoted host changed, not a repricing). Net of all changes, the blended price is -58.3% against 2026-08-17.

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