DeepSeek V4.1 Flash 1017 API Pricing and Speed
DeepSeek V4.1 Flash 1017 API pricing: $0.30 per 1M tokens for input and $1.20 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: $0.0060 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.
Quality on your task: not measured by Measured Lab yet. On our data, DeepSeek V4.1 Flash 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: $5.85 for 5,000 customer messages a month
- Unknown Pull data from invoices and documents with strict JSON and page images: not confirmed, a strict JSON schema request was refused in our test call on 17 Oct 2026
- Calculated Summarize documents and meetings: $2.79 for 1,000 documents or meetings a month
- Calculated Translate content: $4.14 for 3,000 pages a month
- Calculated Chat assistant on your website: $59.85 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $17.02 for 500 coding tasks a month
What our data confirms
- Observed Calls your tools: accepted in our test call on 17 Oct 2026
- Published Reads images; OpenRouter listing, 9 Nov 2026
Example to try
“Draft a reply to this refund request from our returns policy, and hand it to a person if the order is over $500.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 0.8 s, 156 tokens/s (median of 115 test requests on 23 dates, short request)
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
- $0.30Input per 1M tokens, from DeepSeek Published
- $1.20Output per 1M tokens, from DeepSeek Published
- $0.006Cached input per 1M tokens, from DeepSeek Published
OpenRouter listing $0.006 / $0.50 per 1M tokens: listing differs from 49 of 50 endpoints read on 9 Nov 2026.
All prices by channel
| Price per 1M tokens | DeepSeek direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.30 Published | $0.006–$0.60 Publishedacross 50 endpoints; listing $0.006: listing differs from 49 of 50 endpoints | OpenRouter: |
| Output | $1.20 Published | $0.15–$2.40 Publishedacross 50 endpoints; listing $0.50: listing differs from 49 of 50 endpoints | OpenRouter: |
| Cached input · read | $0.006 Published | $0.005 Published | — |
| Batch · input / output | — | $0.011 / $0.20 Published | — |
Input price from DeepSeek, 18 Oct 2026 – 5 Nov 2026
18 Oct 2026$0.30 throughout5 Nov 2026
Input price through OpenRouter, 18 Oct 2026 – 9 Nov 2026
18 Oct 2026$0.15 → $0.006 (7 changes)9 Nov 2026
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 $0.006 · Relace (relace/fp4); output $0.15 · Sail Research (sail-research/fp4/us); status code -5 for sail-research/fp4/us in this reading
Unpinned range: input $0.006–$0.60, output $0.15–$2.40 across 50 endpoints of 40 providers (listing shows $0.165 / $0.68).
No endpoint in this reading sells at the listing price.
Price moves of 20% or more since the reading of 8 Nov 2026:
- Listing price $0.30 / $1.20 → $0.165 / $0.68 (input −45%, output −43%).
- PrimeIntellect (primeintellect): $0.1092 / $1.20 → $0.08736 / $1.20 (input −20%, output 0%).
- Baidu (baidu/fp8): $0.09772 / $0.39437 → $0.28 / $1.13 (input +187%, output +187%).
- DeepSeek (deepseek): $0.15 / $0.60 → $0.30 / $1.20 (input +100%, output +100%).
Observed unpinned cost: 126 short requests sent without a pinned provider on 27 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 | 27 Oct 2026 – 9 Nov 2026 (14 dates) | 12 of 42 InferenceNet (inference-net/us), 11 of 42 Relace (relace/fp4), 6 of 42 Wafer (wafer/mxfp4), 5 of 42 Wafer (wafer/us), 3 of 42 Relace (relace), 2 of 42 DeepInfra (deepinfra/fp8), 2 of 42 Particle AI (particle-ai/us), 1 of 42 Morph (morph/fp8) | $0.00076 | $0.0017 | 0.44× | 0 of 42 |
:floor | 42 | 27 Oct 2026 – 9 Nov 2026 (14 dates) | 21 of 42 OpenInference (open-inference/fp4), 15 of 42 Relace (relace/fp4), 6 of 42 Particle AI (particle-ai/us/flex) | $0.00089 | $0.0018 | 0.48× | 9 of 42 |
:nitro | 42 | 27 Oct 2026 – 9 Nov 2026 (14 dates) | 36 of 42 Together (together), 3 of 42 Relace (relace/fast), 2 of 42 BaseTen (baseten/fast), 1 of 42 CoreWeave (coreweave/fp8) | $0.0022 | $0.0018 | 1.20× | 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 Sail Research (sail-research/fp4/us):
{"provider": {"order": ["sail-research/fp4/us"], "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 (50), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens | Status code |
|---|---|---|---|---|---|---|
| Relace | relace/fp4 | fp4 | $0.006 | $0.50 | 1,048,576 | 0 |
| OpenInference | open-inference/fp4 | fp4 | $0.0175 | $0.70 | 1,048,576 | 0 |
| Morph | morph/fp8 | fp8 | $0.022 | $0.40 | 1,048,576 | 0 |
| Particle AI | particle-ai/us/flex | Not stated | $0.025 | $0.25 | 1,048,576 | 0 |
| Wafer | wafer/us | mxfp4 | $0.038 | $0.50 | 1,048,576 | 0 |
| Particle AI | particle-ai/us | Not stated | $0.05 | $0.50 | 1,048,576 | 0 |
| Wafer | wafer/mxfp4 | mxfp4 | $0.066 | $0.50 | 1,048,576 | 0 |
| DeepInfra | deepinfra/fp8/flex | fp8 | $0.0784 | $0.2352 | 1,048,576 | 0 |
| InferenceNet | inference-net/fp8 | fp8 | $0.08 | $0.55 | 1,040,000 | 0 |
| InferenceNet | inference-net/us | fp8 | $0.08 | $0.55 | 1,040,000 | 0 |
| PrimeIntellect | primeintellect | Not stated | $0.08736 | $1.20 | 1,048,576 | 0 |
| DeepInfra | deepinfra/fp8 | fp8 | $0.098 | $0.294 | 1,048,576 | 0 |
| Cloudflare | cloudflare | Not stated | $0.10 | $0.60 | 1,048,576 | 0 |
| Sail Research | sail-research/fp4/us | fp4 | $0.101 | $0.15 | 1,048,576 | -5 |
| StreamLake | streamlake/fp8 | fp8 | $0.111 | $0.444 | 1,024,000 | 0 |
| Decart | decart/fp8 | fp8 | $0.123 | $0.492 | 1,048,576 | 0 |
| StepFun | stepfun/fp8 | fp8 | $0.135 | $0.54 | 1,000,000 | 0 |
| DeepInfra | deepinfra/fp8/priority | fp8 | $0.147 | $0.441 | 1,048,576 | 0 |
| Alibaba | alibaba | Not stated | $0.15 | $0.60 | 1,000,000 | 0 |
| Makora | makora/fp8 | fp8 | $0.15 | $1.20 | 1,048,576 | 0 |
| Sail Research | sail-research/fp4 | fp4 | $0.1515 | $0.225 | 1,048,576 | -5 |
| Reka | reka | Not stated | $0.16 | $1.10 | 1,048,576 | 0 |
| Ionstream | ionstream | Not stated | $0.165 | $0.495 | 1,048,576 | 0 |
| Novita | novita/fp8 | fp8 | $0.165 | $0.66 | 1,048,576 | 0 |
| ModelRun | modelrun/fp4 | fp4 | $0.17 | $0.67 | 1,048,576 | 0 |
| DekaLLM | dekallm | Not stated | $0.18 | $0.68 | 1,048,576 | 0 |
| DigitalOcean | digitalocean | Not stated | $0.18 | $0.72 | 1,048,576 | 0 |
| GMICloud | gmicloud/fp8 | fp8 | $0.18 | $0.72 | 1,048,575 | 0 |
| Cohere | cohere/fp8 | fp8 | $0.195 | $0.66 | 1,048,576 | 0 |
| AtlasCloud | atlas-cloud/fp8 | fp8 | $0.195 | $0.78 | 1,048,576 | 0 |
| Phala | phala | Not stated | $0.20 | $1.20 | 1,048,576 | 0 |
| Fireworks | fireworks/spot | Not stated | $0.21 | $0.84 | 1,048,576 | -5 |
| PrimaLabs | primalabs | Not stated | $0.24 | $0.96 | 1,048,576 | 0 |
| Modal | modal | Not stated | $0.25 | $1.00 | 1,048,576 | 0 |
| Baidu | baidu/fp8 | fp8 | $0.28 | $1.13 | 1,048,576 | 0 |
| Crusoe | crusoe/fp8 | fp8 | $0.29 | $1.20 | 1,048,576 | 0 |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.30 | $0.55 | 1,048,576 | 0 |
| Relace | relace/fast | fp4 | $0.30 | $0.90 | 1,048,576 | 0 |
| BaseTen | baseten | Not stated | $0.30 | $1.20 | 1,048,576 | 0 |
| CoreWeave | coreweave/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 | 0 |
10 more endpoints in the source.
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 | 772 msrange 0.43–1.25 s · slow 10 %: 979 ms Observed | 156 tokens/srange 92.5–218 · slowest 10 %: 130 tokens/s | — | Hidden by providerthe API does not report it |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off110 answers on 22 dates · 100 % answered | 830 msrange 0.38–1.26 s · slow 10 %: 993 ms Observed | 153 tokens/srange 99.6–211 · slowest 10 %: 128 tokens/s | — | Hidden by providerthe API does not report it |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off110 answers on 22 dates · 100 % answered | 761 msrange 0.38–1.13 s · slow 10 %: 926 ms Observed | 160 tokens/srange 102–514 · slowest 10 %: 132 tokens/s | — | Hidden by providerthe API does not report it |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off110 answers on 22 dates · 100 % answered | 805 msrange 0.41–1.73 s · slow 10 %: 985 ms Observed | 158 tokens/srange 90.1–354 · slowest 10 %: 137 tokens/s | — | Hidden by providerthe API does not report it |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · DeepSeekreasoning: off110 answers on 22 dates · 100 % answered | 808 msrange 0.34–1.92 s · slow 10 %: 985 ms Observed | 155 tokens/srange 106–209 · slowest 10 %: 138 tokens/s | — | Hidden by providerthe API does not report it |
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 | 98 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code98 % on 22 Oct 2026 · 98 % on 17 Oct 2026 · instruction level 99 % |
- 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.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 18 Oct 2026
- Shown in: the United States
- Checks so far: 23 checks since 18 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 V4.1 Flash (peak rate) cost per 1M cache-read tokens (cache hits) directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4.1 Flash (peak rate) cost per 1M input tokens directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4.1 Flash (peak rate) cost per 1M output tokens directly from DeepSeek (official API price)? | Unknown | Unknown | |
| How much does DeepSeek V4.1 Flash 1017 cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.0050 per 1M tokens | Published | |
| How much does DeepSeek V4.1 Flash 1017 cost per 1M output tokens on OpenRouter? | $0.50 per 1M tokens | Published | |
| What is the context window of DeepSeek V4.1 Flash 1017 on OpenRouter, in tokens? | 1,048,576 tokens | Published | |
| What is the maximum output length of DeepSeek V4.1 Flash 1017 on OpenRouter, in tokens? | 943,718 tokens | Published |
History
- — $1.20 per 1M tokens → $0.50 per 1M tokens (How much does DeepSeek V4.1 Flash 1017 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.
- — $0.30 per 1M tokens → $0.0060 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.
- — $0.0060 per 1M tokens → $0.0050 per 1M tokens (How much does DeepSeek V4.1 Flash 1017 cost per 1M cache-read tokens (cache hits) 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.
- — 393,216 tokens → 943,718 tokens (What is the maximum output length of DeepSeek V4.1 Flash 1017 on OpenRouter, in tokens?) Confirmed by the check on 9 Nov 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
- — First check: $0.15 per 1M tokens
- Short-lived or unconfirmed moves are not shown as changes.
The source record lists $0.000000006 per token ($0.0060 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.000000006"
Briefings on this model each price change recalculated as a task cost
- 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 %)
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Record history — 174 records for 8 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.0060 per 1M tokens | Published |
| 8 Nov 2026 | $0.0060 per 1M tokens | Published |
| 7 Nov 2026 | $0.15 per 1M tokens | Published |
| 6 Nov 2026 | $0.30 per 1M tokens | Published |
| 5 Nov 2026 | $0.30 per 1M tokens | Published |
| 4 Nov 2026 | $0.30 per 1M tokens | Published |
| 3 Nov 2026 | $0.30 per 1M tokens | Published |
| 2 Nov 2026 | $0.30 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 | $0.0060 per 1M tokens | Published |
| 4 Nov 2026 | $0.0060 per 1M tokens | Published |
| 3 Nov 2026 | $0.0060 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 | $0.30 per 1M tokens | Published |
| 4 Nov 2026 | $0.30 per 1M tokens | Published |
| 3 Nov 2026 | $0.30 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 | $1.20 per 1M tokens | Published |
| 4 Nov 2026 | $1.20 per 1M tokens | Published |
| 3 Nov 2026 | $1.20 per 1M tokens | Published |
| 2 Nov 2026 | $1.20 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.0050 per 1M tokens | Published |
| 8 Nov 2026 | $0.0050 per 1M tokens | Published |
| 7 Nov 2026 | $0.0030 per 1M tokens | Published |
| 6 Nov 2026 | $0.0060 per 1M tokens | Published |
| 5 Nov 2026 | $0.0060 per 1M tokens | Published |
| 4 Nov 2026 | $0.0060 per 1M tokens | Published |
| 3 Nov 2026 | $0.0060 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.50 per 1M tokens | Published |
| 8 Nov 2026 | $0.50 per 1M tokens | Published |
| 7 Nov 2026 | $0.60 per 1M tokens | Published |
| 6 Nov 2026 | $1.20 per 1M tokens | Published |
| 5 Nov 2026 | $1.20 per 1M tokens | Published |
| 4 Nov 2026 | $1.20 per 1M tokens | Published |
| 3 Nov 2026 | $1.20 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 |
| 2 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 | 393,216 tokens | Published |
| 6 Nov 2026 | 393,216 tokens | Published |
| 5 Nov 2026 | 393,216 tokens | Published |
| 4 Nov 2026 | 393,216 tokens | Published |
| 3 Nov 2026 | 393,216 tokens | Published |
| 2 Nov 2026 | 393,216 tokens | Published |
Showing the latest 60 of 174 records; the full history is in data.json and data.csv.