DeepSeek V4 Pro 0813 API Pricing and Speed
DeepSeek V4 Pro 0813 API pricing: $1.32 per 1M tokens for input and $3.96 per 1M tokens for output, from the official API price list of DeepSeek. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.11 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 8 Nov 2026.
Price changed 8 Nov 2026. output $4.00 → $4.44 (+11.0 %); input $0.115 → $0.111 (−3.5 %) per 1M tokens on OpenRouter. Confirmed by a later check on 9 Nov 2026. Briefing: what it does to task costs
Quality on your task: not measured by Measured Lab yet. On our data, DeepSeek V4 Pro fits 5 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $23.43 for 5,000 customer messages a month
- Unknown Pull data from invoices and documents with strict JSON and page images: not confirmed, reads text only, per the OpenRouter listing; strict JSON output partly, per DeepSeek’s documentation
- Calculated Summarize documents and meetings: $11.62 for 1,000 documents or meetings a month
- Calculated Translate content: $14.65 for 3,000 pages a month
- Calculated Chat assistant on your website: $251.46 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $72.27 for 500 coding tasks a month
What our data confirms
- Published Calls your tools, in DeepSeek documentation, read 17 Oct 2026
- Published Reads text only; OpenRouter listing, 9 Nov 2026
- Published Weights on Hugging Face: deepseek-ai/DeepSeek-V4-Pro-0813, as linked by the OpenRouter listing
Example to try
“Review this pull request and list bugs and missing tests, with the file and line of each.” Run it on your own data before you choose.
What we measured
- Unknown Speed on a short test request: Unknown
Stated by the provider
- Stated by the provider DeepSeek for this model: Terminal-Bench 2.1 87.9, DeepSWE 62.7; quotes and test conditions in Quality signals
Before you choose
- Published Training on your data, per DeepSeek Terms of Use: yes — de-identified Inputs and Outputs, with an opt-out ("Improve the model for everyone"), read 9 Nov 2026
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $1.32Input per 1M tokens, from DeepSeek Published
- $3.96Output per 1M tokens, from DeepSeek Published
- $0.044Cached input per 1M tokens, from DeepSeek Published
OpenRouter listing $0.111 / $4.44 per 1M tokens: listing differs from 24 of 25 endpoints read on 9 Nov 2026.
All prices by channel
| Price per 1M tokens | DeepSeek direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $1.32 Published | $0.0999–$1.98 Publishedacross 25 endpoints; listing $0.111: listing differs from 24 of 25 endpoints | OpenRouter: |
| Output | $3.96 Published | $1.98–$8.00 Publishedacross 25 endpoints; listing $4.44: listing differs from 24 of 25 endpoints | OpenRouter: |
| Cached input · read | $0.044 Published | $0.097 Published | — |
Input price from DeepSeek, 16 Oct 2026 – 5 Nov 2026
16 Oct 2026$1.32 throughout5 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.66 → $0.111 (8 changes)9 Nov 2026
Context window1,048,576tokens Published
Max output943,718tokens 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: input $0.0999 · Relace (relace/fp4); output $1.98 · StreamLake (streamlake)
Unpinned range: input $0.0999–$1.98, output $1.98–$8.00 across 25 endpoints of 21 providers (listing shows $1.32 / $3.96).
Price moves of 20% or more since the reading of 8 Nov 2026:
- Listing price $0.103 / $4.11 → $1.32 / $3.96 (input +1182%, output −4%).
- Baidu (baidu/fp8): $0.65868 / $1.97604 → $1.32 / $3.96 (input +100%, output +100%).
- DeepSeek (deepseek): $0.66 / $1.98 → $1.32 / $3.96 (input +100%, output +100%).
Observed unpinned cost: 126 short requests sent without a pinned provider on 25 Oct 2026 – 9 Nov 2026 (14 dates), in each routing mode. Charged is the sum of the OpenRouter generation receipts for these requests; the listing price column is the price of the same input and output tokens at the listing price of that date.
| Routing mode | Requests | Dates | Served by | Charged | Listing price for the same tokens | Charged / listing | Lowest-priced endpoint answered |
|---|---|---|---|---|---|---|---|
| Default (no provider field) | 42 | 25 Oct 2026 – 9 Nov 2026 (14 dates) | 23 of 42 Sail Research (sail-research/us), 5 of 42 Nebius (nebius/fp8), 4 of 42 Ionstream (ionstream), 3 of 42 Baidu (baidu/fp8), 3 of 42 Cloudflare (cloudflare), 2 of 42 Together (together), 1 of 42 CoreWeave (coreweave/fp8), 1 of 42 Parasail (parasail/fp8) | $0.0029 | $0.0039 | 0.72× | 13 of 42 |
:floor | 42 | 25 Oct 2026 – 9 Nov 2026 (14 dates) | 41 of 42 Relace (relace/fp4), 1 of 42 Wafer (wafer/mxfp4) | $0.010 | $0.0089 | 1.06× | 0 of 42 |
:nitro | 42 | 25 Oct 2026 – 9 Nov 2026 (14 dates) | 24 of 42 CoreWeave (coreweave/fp8), 6 of 42 DigitalOcean (digitalocean), 6 of 42 Wafer (wafer/mxfp4), 3 of 42 Sail Research (sail-research/us), 3 of 42 Together (together) | $0.0083 | $0.0070 | 1.08× | 0 of 42 |
Routing modes as documented by OpenRouter (OpenRouter provider routing, read 25 Oct 2026): the default request has no provider field; :floor and :nitro are suffixes of the model name. Served by names the endpoint that answered, by the provider name and endpoint tag of the receipt. Each request asks for one short line with an answer cap of 32 tokens. The counts are for these requests on these dates only.
Models with the widest provider price spread on OpenRouter
Request fragment that pins Relace (relace/fp4):
{"provider": {"order": ["relace/fp4"], "allow_fallbacks": false}}Request fragment that pins StreamLake (streamlake):
{"provider": {"order": ["streamlake"], "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 (25), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens | Status code |
|---|---|---|---|---|---|---|
| Relace | relace/fp4 | fp4 | $0.0999 | $8.00 | 1,048,576 | 0 |
| Wafer | wafer/us | mxfp4 | $0.111 | $4.44 | 1,048,576 | 0 |
| Wafer | wafer/mxfp4 | mxfp4 | $0.285 | $4.30 | 1,048,576 | 0 |
| StreamLake | streamlake | Not stated | $0.66 | $1.98 | 1,024,000 | 0 |
| Novita | novita/fp8 | fp8 | $0.99 | $2.97 | 1,048,576 | 0 |
| GMICloud | gmicloud/fp8 | fp8 | $1.056 | $3.168 | 1,048,575 | 0 |
| Alibaba | alibaba | Not stated | $1.122 | $3.366 | 1,000,000 | -2 |
| DeepInfra | deepinfra/fp8 | fp8 | $1.30 | $2.60 | 1,048,576 | 0 |
| CoreWeave | coreweave/fp8 | fp8 | $1.31 | $3.96 | 1,048,576 | 0 |
| Alibaba | alibaba/us-east-1 | Not stated | $1.32 | $3.96 | 1,000,000 | 0 |
| AtlasCloud | atlas-cloud/fp8 | fp8 | $1.32 | $3.96 | 1,048,576 | 0 |
| Baidu | baidu/fp8 | fp8 | $1.32 | $3.96 | 1,048,576 | 0 |
| BaseTen | baseten/fp4 | fp4 | $1.32 | $3.96 | 1,048,576 | 0 |
| Cloudflare | cloudflare | Not stated | $1.32 | $3.96 | 1,048,576 | 0 |
| DeepSeek | deepseek | Not stated | $1.32 | $3.96 | 1,048,576 | 0 |
| DigitalOcean | digitalocean | Not stated | $1.32 | $3.96 | 1,048,576 | 0 |
| Nebius | nebius/fp8 | fp8 | $1.32 | $3.96 | 1,048,576 | 0 |
| Parasail | parasail/fp8 | fp8 | $1.32 | $3.96 | 1,048,576 | 0 |
| SiliconFlow | siliconflow/fp8 | fp8 | $1.32 | $3.96 | 1,048,576 | 0 |
| Together | together | Not stated | $1.32 | $3.96 | 1,048,576 | 0 |
| Sail Research | sail-research/fp4 | fp4 | $1.35 | $2.40 | 1,048,576 | 0 |
| Sail Research | sail-research/us | fp4 | $1.35 | $2.40 | 1,048,576 | 0 |
| Phala | phala | Not stated | $1.45 | $4.36 | 1,048,576 | 0 |
| Venice | venice | Not stated | $1.65 | $4.95 | 1,000,000 | -2 |
| Parasail | parasail/fast | fp8 | $1.98 | $5.94 | 1,048,576 | 0 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list. Status code is the status field of the endpoints list, as read.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off115 answers on 23 dates · 100 % answered | 984 msrange 0.53–1.48 s · slow 10 %: 1.25 s Observed | 75.5 tokens/srange 38.4–130 · slowest 10 %: 53.1 tokens/s | $0.000726range $0.000463–$0.000729 Calculated | Hidden by providerthe API does not report it |
| Hosted by BytePlusreasoning: off110 answers on 22 dates · 100 % answered | 1.86 srange 1.31–3.07 s · slow 10 %: 2.23 s Observed | 57.5 tokens/srange 45.0–74.0 · slowest 10 %: 51.6 tokens/s | $0.000726range $0.000723–$0.00073 Calculated | 0for 64 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off105 answers on 21 dates · 100 % answered | 1.03 srange 0.51–4.60 s · slow 10 %: 1.61 s Observed | 69.1 tokens/srange 34.1–129 · slowest 10 %: 50.8 tokens/s | $0.000726range $0.000723–$0.000729 Calculated | Hidden by providerthe API does not report it |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off105 answers on 21 dates · 100 % answered | 962 msrange 0.51–4.70 s · slow 10 %: 1.49 s Observed | 70.2 tokens/srange 41.7–132 · slowest 10 %: 49.6 tokens/s | $0.000726range $0.000723–$0.000729 Calculated | Hidden by providerthe API does not report it |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off105 answers on 21 dates · 100 % answered | 1.01 srange 0.52–1.74 s · slow 10 %: 1.40 s Observed | 76.0 tokens/srange 36.9–125 · slowest 10 %: 52.9 tokens/s | $0.000726range $0.000723–$0.000729 Calculated | Hidden by providerthe API does not report it |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off105 answers on 21 dates · 100 % answered | 958 msrange 0.41–1.40 s · slow 10 %: 1.23 s Observed | 76.4 tokens/srange 37.7–133 · slowest 10 %: 52.2 tokens/s | $0.000726range $0.000723–$0.00073 Calculated | Hidden by providerthe API does not report it |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
| Signal | Result | Source |
|---|---|---|
| Instruction followingIFEval, 50 prompts · reasoning: off | 92 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code92 % on 22 Oct 2026 · 94 % on 17 Oct 2026 · instruction level 93 % |
Figures the provider publishes (4)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| Humanity's Last Exam (HLE) | 42.7 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4-Pro-0813 · Hugging Faceread 17 Oct 2026 |
| Humanity's Last Exam (HLE), with tools | 60.0 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4-Pro-0813 · Hugging Faceread 17 Oct 2026 |
| Terminal-Bench 2.1 | 87.9 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4-Pro-0813 · Hugging Faceread 17 Oct 2026 |
| DeepSWE | 62.7 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4-Pro-0813 · Hugging Faceread 17 Oct 2026 |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
What typical tasks cost with this model
| Task | At DeepSeek's price (Unknown) | Through OpenRouter ($0.111 / $4.44) |
|---|---|---|
| 1,000 chat replies | Unknown | $1.44 |
| Summarizing 100 documents | Unknown | $0.22 |
| A day of coding assistant use | Unknown | $0.84 |
Calculated Prices per 1M tokens (input / output) in brackets; token counts and what is not included: our assumptions and the same tasks on other models.
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
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does DeepSeek V4 Pro 0813 (peak rate) cost per 1M cache-read tokens (cache hits) directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4 Pro 0813 (peak rate) cost per 1M input tokens directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4 Pro 0813 (peak rate) cost per 1M output tokens directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4 Pro 0813 cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.10 per 1M tokens | Published | |
| How much does DeepSeek V4 Pro 0813 cost per 1M output tokens on OpenRouter? | $4.44 per 1M tokens | Published | |
| What is the context window of DeepSeek V4 Pro 0813 on OpenRouter, in tokens? | 1,048,576 tokens | Published | |
| What is the maximum output length of DeepSeek V4 Pro 0813 on OpenRouter, in tokens? | 943,718 tokens | Published |
History
- — $0.12 per 1M tokens → $0.11 per 1M tokens Confirmed by the check on 9 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.
- — $4.00 per 1M tokens → $4.44 per 1M tokens (How much does DeepSeek V4 Pro 0813 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 9 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.
- — $0.04 per 1M tokens → $0.11 per 1M tokens (How much does DeepSeek V4 Pro 0813 cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 2 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.
- — 393,216 tokens → 943,718 tokens (What is the maximum output length of DeepSeek V4 Pro 0813 on OpenRouter, in tokens?) Confirmed by the check on 2 Nov 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
- — $1.32 per 1M tokens → $0.12 per 1M tokens Confirmed by the check on 2 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.
- — $3.96 per 1M tokens → $4.00 per 1M tokens (How much does DeepSeek V4 Pro 0813 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 2 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.
- — First check: $0.66 per 1M tokens
- Short-lived or unconfirmed moves are not shown as changes.
The source record lists $0.00000011 per token ($0.11 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.000000111"
Briefings on this model each price change recalculated as a task cost
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4 Pro 0813: price cut input $1.32 → $0.115 per 1M tokens (-91 %), output $3.96 → $4.00 per 1M tokens (+1 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
Record history — 187 records for 8 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.11 per 1M tokens | Published |
| 8 Nov 2026 | $0.11 per 1M tokens | Published |
| 7 Nov 2026 | $0.12 per 1M tokens | Published |
| 6 Nov 2026 | $0.10 per 1M tokens | Published |
| 5 Nov 2026 | $0.12 per 1M tokens | Published |
| 4 Nov 2026 | $0.12 per 1M tokens | Published |
| 3 Nov 2026 | $0.12 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | $0.04 per 1M tokens | Published |
| 4 Nov 2026 | $0.04 per 1M tokens | Published |
| 3 Nov 2026 | $0.04 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | $1.32 per 1M tokens | Published |
| 4 Nov 2026 | $1.32 per 1M tokens | Published |
| 3 Nov 2026 | $1.32 per 1M tokens | Published |
| 2 Nov 2026 | $1.32 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | Unknown | Unknown |
| 8 Nov 2026 | Unknown | Unknown |
| 7 Nov 2026 | Unknown | Unknown |
| 6 Nov 2026 | Unknown | Unknown |
| 5 Nov 2026 | $3.96 per 1M tokens | Published |
| 4 Nov 2026 | $3.96 per 1M tokens | Published |
| 3 Nov 2026 | $3.96 per 1M tokens | Published |
| 2 Nov 2026 | $3.96 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.10 per 1M tokens | Published |
| 8 Nov 2026 | $0.11 per 1M tokens | Published |
| 7 Nov 2026 | $0.11 per 1M tokens | Published |
| 6 Nov 2026 | $0.10 per 1M tokens | Published |
| 5 Nov 2026 | $0.11 per 1M tokens | Published |
| 4 Nov 2026 | $0.11 per 1M tokens | Published |
| 3 Nov 2026 | $0.11 per 1M tokens | Published |
| 2 Nov 2026 | $0.11 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $4.44 per 1M tokens | Published |
| 8 Nov 2026 | $4.44 per 1M tokens | Published |
| 7 Nov 2026 | $4.66 per 1M tokens | Published |
| 6 Nov 2026 | $4.11 per 1M tokens | Published |
| 5 Nov 2026 | $4.60 per 1M tokens | Published |
| 4 Nov 2026 | $4.00 per 1M tokens | Published |
| 3 Nov 2026 | $4.00 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 1,048,576 tokens | Published |
| 8 Nov 2026 | 1,048,576 tokens | Published |
| 7 Nov 2026 | 1,048,576 tokens | Published |
| 6 Nov 2026 | 1,048,576 tokens | Published |
| 5 Nov 2026 | 1,048,576 tokens | Published |
| 4 Nov 2026 | 1,048,576 tokens | Published |
| 3 Nov 2026 | 1,048,576 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 943,718 tokens | Published |
| 8 Nov 2026 | 943,718 tokens | Published |
| 7 Nov 2026 | 943,718 tokens | Published |
| 6 Nov 2026 | 943,718 tokens | Published |
| 5 Nov 2026 | 943,718 tokens | Published |
| 4 Nov 2026 | 943,718 tokens | Published |
| 3 Nov 2026 | 943,718 tokens | Published |
| 2 Nov 2026 | 943,718 tokens | Published |
Showing the latest 60 of 187 records; the full history is in data.json and data.csv.