DeepSeek V4 Pro 0423 API Pricing

DeepSeek V4 Pro 0423 API pricing: $0.95526 per 1M tokens for input and $1.91052 per 1M tokens for output, from OpenRouter. Published Last checked · Source (data) · Methodology

OpenRouter: Amount worked out from the source page: $0.96 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · last price change seen on 31 Oct 2026.

Data as of9 Nov 2026Prices checked 9 Nov 2026 · test requests to 8 Nov 2026Data & API
Price changed 31 Oct 2026. output $1.91052 → $3.20 (+67.5 %); input $0.95526 → $1.60 (+67.5 %) per 1M tokens on OpenRouter. Confirmed by a later check on 1 Nov 2026. Briefing: what it does to task costs
Task receipt: OpenRouter: $0.158; Warm cache: $0.034 Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.124 per task. Dashed outline: the no-cache bill.
Task receipt.Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.124 per task. Dashed outline: the no-cache bill. Open image · Explore the chart · Measured Lab · CC BY 4.0

Prices USD per 1M tokens, as listed

  • $0.95526Input per 1M tokens, through OpenRouter Published
  • $1.91052Output per 1M tokens, through OpenRouter Published
All prices by channel
Price per 1M tokensProvider directThrough OpenRouterPrevious prices by channel
Input—$0.95526 PublishedOpenRouter: $0.95526 until 31 Oct 2026
Output—$1.91052 PublishedOpenRouter: $1.91052 until 31 Oct 2026
Cached input · read—$0.079605 Published—

Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026

16 Oct 2026$0.297192 → $0.95526 (12 changes)9 Nov 2026

Context window1,048,576tokens Published
Max output384,000tokens Published

OpenRouter providers who serves this model through OpenRouter, at what price

OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.

Pinned min: $0.90 / $1.50 · Relace (relace/fp4)

Unpinned range: input $0.90–$1.91, output $1.50–$3.83 across 14 endpoints of 13 providers.

Price moves of 20% or more since the reading of 8 Nov 2026:

  • StreamLake (streamlake/fp8): $0.454314 / $0.908628 → $0.95526 / $1.91052 (input +110%, output +110%).
  • Baidu (baidu/fp8): $0.45292 / $0.90584 → $1.69 / $3.38 (input +273%, output +273%).
  • Lowest-priced endpoint for the workload: Relace (relace/fp4) at $7.32 per 1,000 tasks, before Baidu (baidu/fp8) at $3.76.

Models with the widest provider price spread on OpenRouter

Request fragment that pins Relace (relace/fp4):

{"provider": {"order": ["relace/fp4"], "allow_fallbacks": false}}

With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).

All endpoints (14), by input price
ProviderEndpoint tagPrecisionInputOutputContext, tokens
Relacerelace/fp4fp4$0.90$1.501,048,576
StreamLakestreamlake/fp8fp8$0.95526$1.910521,024,000
GMICloudgmicloud/fp8fp8$0.957$1.9141,048,576
SiliconFlowsiliconflow/fp8fp8$1.00$1.501,048,576
DigitalOceandigitaloceanNot stated$1.044$2.0881,048,576
DeepInfradeepinfra/fp8fp8$1.30$2.601,048,576
Alibabaalibaba/fp8fp8$1.416$2.8321,000,000
Alibabaalibaba/fp8/us-east-1fp8$1.56$3.121,000,000
Novitanovita/fp8fp8$1.60$3.201,048,576
VeniceveniceNot stated$1.65$3.3011,000,000
AtlasCloudatlas-cloud/fp4fp4$1.68$3.381,048,576
Baidubaidu/fp8fp8$1.69$3.381,048,576
Nebiusnebius/fp8fp8$1.75$3.501,048,576
Azureazure/usNot stated$1.91$3.831,048,576

Sorted by input price, then output price. Precision is the quantization field of the endpoints list.

Newer snapshot. The API name deepseek-v4-pro now serves DeepSeek: DeepSeek V4 Pro 0813 (provider’s page). This page keeps the earlier snapshot 0423 as listed on OpenRouter.

How we got this number

  • What we read: the published price on openrouter.ai/api/v1/models
  • Checked: ; tracked since 16 Oct 2026
  • Shown in: the United States
  • Checks so far: 25 checks since 16 Oct 2026
  • What changed: the price last changed on ; every change is listed under History
  • Page updated:

Other measured facts

QuestionAnswerCheckedStatus
How much does DeepSeek V4 Pro 0423 cost per 1M cache-read tokens (cache hits) on OpenRouter?$0.08 per 1M tokensPublished
How much does DeepSeek V4 Pro 0423 cost per 1M output tokens on OpenRouter?$1.91 per 1M tokensPublished
What is the context window of DeepSeek V4 Pro 0423 on OpenRouter, in tokens?1,048,576 tokensPublished
What is the maximum output length of DeepSeek V4 Pro 0423 on OpenRouter, in tokens?384,000 tokensPublished

History

  1. — $0.96 per 1M tokens → $1.60 per 1M tokens Confirmed by the check on 1 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  2. — $1.91 per 1M tokens → $3.20 per 1M tokens (How much does DeepSeek V4 Pro 0423 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 1 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  3. — $0.08 per 1M tokens → $0.14 per 1M tokens (How much does DeepSeek V4 Pro 0423 cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 1 Nov 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  4. — $0.30 per 1M tokens → $0.96 per 1M tokens Confirmed by the check on 20 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  5. — $0.59 per 1M tokens → $1.91 per 1M tokens (How much does DeepSeek V4 Pro 0423 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 20 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  6. — First check: $0.30 per 1M tokens
  7. Short-lived or unconfirmed moves are not shown as changes.

The source record lists $0.00000096 per token ($0.96 per 1M tokens), fetched on 9 Nov 2026.

The source record, as published
"prompt":"0.00000095526"
What the source says · openrouter.ai

Briefings on this model each price change recalculated as a task cost

  1. DeepSeek V4 Pro 0423: price rise input $0.955 → $1.60 per 1M tokens (+67 %), output $1.91 → $3.20 per 1M tokens (+67 %)
  2. DeepSeek V4 Pro 0423: price rise input $0.297 → $0.955 per 1M tokens (+221 %), output $0.594 → $1.91 per 1M tokens (+221 %)
  3. DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)

All briefings

Record history — 113 records for 5 questions
Last record
Shown in
the United States
How much does DeepSeek V4 Pro 0423 cost per 1M input tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.96 per 1M tokensPublished
8 Nov 2026$0.90 per 1M tokensPublished
7 Nov 2026$0.85 per 1M tokensPublished
6 Nov 2026$0.96 per 1M tokensPublished
5 Nov 2026$1.60 per 1M tokensPublished
4 Nov 2026$1.60 per 1M tokensPublished
3 Nov 2026$1.60 per 1M tokensPublished
2 Nov 2026$1.60 per 1M tokensPublished
1 Nov 2026$1.60 per 1M tokensPublished
31 Oct 2026$1.60 per 1M tokensPublished
30 Oct 2026$0.82 per 1M tokensPublished
29 Oct 2026$0.96 per 1M tokensPublished
How much does DeepSeek V4 Pro 0423 cost per 1M cache-read tokens (cache hits) on OpenRouter?
TimeValueStatus
9 Nov 2026$0.08 per 1M tokensPublished
8 Nov 2026$0.25 per 1M tokensPublished
7 Nov 2026$0.07 per 1M tokensPublished
6 Nov 2026$0.08 per 1M tokensPublished
5 Nov 2026$0.14 per 1M tokensPublished
4 Nov 2026$0.14 per 1M tokensPublished
3 Nov 2026$0.14 per 1M tokensPublished
2 Nov 2026$0.14 per 1M tokensPublished
1 Nov 2026$0.14 per 1M tokensPublished
31 Oct 2026$0.14 per 1M tokensPublished
30 Oct 2026$0.07 per 1M tokensPublished
29 Oct 2026$0.08 per 1M tokensPublished
How much does DeepSeek V4 Pro 0423 cost per 1M output tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$1.91 per 1M tokensPublished
8 Nov 2026$1.50 per 1M tokensPublished
7 Nov 2026$1.70 per 1M tokensPublished
6 Nov 2026$1.91 per 1M tokensPublished
5 Nov 2026$3.20 per 1M tokensPublished
4 Nov 2026$3.20 per 1M tokensPublished
3 Nov 2026$3.20 per 1M tokensPublished
2 Nov 2026$3.20 per 1M tokensPublished
1 Nov 2026$3.20 per 1M tokensPublished
31 Oct 2026$3.20 per 1M tokensPublished
30 Oct 2026$1.63 per 1M tokensPublished
29 Oct 2026$1.91 per 1M tokensPublished
What is the context window of DeepSeek V4 Pro 0423 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 20261,048,576 tokensPublished
8 Nov 20261,048,576 tokensPublished
7 Nov 20261,048,576 tokensPublished
6 Nov 20261,048,576 tokensPublished
5 Nov 20261,048,576 tokensPublished
4 Nov 20261,048,576 tokensPublished
3 Nov 20261,048,576 tokensPublished
2 Nov 20261,048,576 tokensPublished
1 Nov 20261,048,576 tokensPublished
31 Oct 20261,048,576 tokensPublished
30 Oct 20261,048,576 tokensPublished
29 Oct 20261,048,576 tokensPublished
What is the maximum output length of DeepSeek V4 Pro 0423 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026384,000 tokensPublished
8 Nov 2026393,216 tokensPublished
7 Nov 2026384,000 tokensPublished
6 Nov 2026384,000 tokensPublished
5 Nov 2026393,216 tokensPublished
4 Nov 2026393,216 tokensPublished
3 Nov 2026393,216 tokensPublished
2 Nov 2026393,216 tokensPublished
1 Nov 2026393,216 tokensPublished
31 Oct 2026393,216 tokensPublished
30 Oct 2026384,000 tokensPublished
29 Oct 2026384,000 tokensPublished

Showing the latest 60 of 113 records; the full history is in data.json and data.csv.

Explore the numbers

DeepSeek V4 Pro 0423

OpenRouter$0.158Warm cache$0.034$0.00$0.05$0.10$0.15$0.20OpenRouter$0.158Warm cache$0.034$0.00$0.05$0.10$0.15$0.20
OpenRouter$2,301.22Warm cache$493.80$0$1,000$2,000$3,000OpenRouter$2,301.22Warm cache$493.80$0$1,000$2,000$3,000

Calculated · Document analysis

Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries.

Warm-cache saving: $0.124 per task. Dashed outline: the no-cache bill.

Assumption: first-step cache fraction 75%; earlier context is read again and new context is written. All calls stay within the cache lifetime.

Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown.

Fresh input · Visible output · Cache read · Cache write

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.