DeepSeek V4.1 Flash 0910 API Pricing and Speed
DeepSeek V4.1 Flash 0910 API pricing: $0.051 per 1M tokens for input and $0.567 per 1M tokens for output, from OpenRouter. Our measured latency and output speed are shown by route and country below. Published Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.05 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 7 Nov 2026.
Price changed 7 Nov 2026. output $0.50 → $0.567 (+13.4 %); input $0.045 → $0.051 (+13.3 %) per 1M tokens on OpenRouter. Confirmed by a later check on 8 Nov 2026.
Prices USD per 1M tokens, as listed
- $0.006–$0.45Input per 1M tokens, through OpenRouter, across 39 endpoints Published
- $0.336–$1.80Output per 1M tokens, through OpenRouter, across 39 endpoints Published
- $0.011Batch input per 1M tokens, through OpenRouter Published
OpenRouter listing $0.051 / $0.567 per 1M tokens: listing differs from 38 of 39 endpoints read on 9 Nov 2026.
All prices by channel
| Price per 1M tokens | Provider direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | — | $0.006–$0.45 Publishedacross 39 endpoints; listing $0.051: listing differs from 38 of 39 endpoints | OpenRouter: |
| Output | — | $0.336–$1.80 Publishedacross 39 endpoints; listing $0.567: listing differs from 38 of 39 endpoints | OpenRouter: |
| Cached input · read | — | $0.018 Published | — |
| Batch · input / output | — | $0.011 / $0.20 Published | — |
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.036 → $0.051 (11 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 $0.006 · Relace (relace/fp4); output $0.336 · DeepInfra (deepinfra/fp8/flex)
Unpinned range: input $0.006–$0.45, output $0.336–$1.80 across 39 endpoints of 30 providers (listing shows $0.21 / $0.84).
Price moves of 20% or more since the reading of 8 Nov 2026:
- Listing price $0.045 / $0.50 → $0.21 / $0.84 (input +367%, output +68%).
- PrimeIntellect (primeintellect): $0.156 / $1.20 → $0.039 / $1.20 (input −75%, output 0%).
- Baidu (baidu/fp8): $0.0507 / $0.2028 → $0.30 / $1.20 (input +492%, output +492%).
Observed unpinned cost: 144 short requests sent without a pinned provider on 25 Oct 2026 – 9 Nov 2026 (16 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) | 48 | 25 Oct 2026 – 9 Nov 2026 (16 dates) | 18 of 48 Relace (relace), 11 of 48 Relace (relace/fp4), 8 of 48 Wafer (wafer/us), 7 of 48 InferenceNet (inference-net/us), 2 of 48 Wafer (wafer/mxfp4), 1 of 48 DeepInfra (deepinfra/fp8), 1 of 48 Sail Research (sail-research/fp4/us) | $0.00093 | $0.0015 | 0.61× | 1 of 48 |
:floor | 48 | 25 Oct 2026 – 9 Nov 2026 (16 dates) | 33 of 48 OpenInference (open-inference/fp4), 12 of 48 Relace (relace/fp4), 3 of 48 Morph (morph/fp8) | $0.0010 | $0.0015 | 0.68× | 7 of 48 |
:nitro | 48 | 25 Oct 2026 – 9 Nov 2026 (16 dates) | 24 of 48 Together (together), 8 of 48 BaseTen (baseten/us), 6 of 48 Wafer (wafer/mxfp4), 3 of 48 Crusoe (crusoe/fp8), 3 of 48 Wafer (wafer/us), 2 of 48 Cohere (cohere), 2 of 48 Fireworks (fireworks/spot) | $0.0022 | $0.0015 | 1.42× | 0 of 48 |
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 DeepInfra (deepinfra/fp8/flex):
{"provider": {"order": ["deepinfra/fp8/flex"], "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 (39), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
| Relace | relace/fp4 | fp4 | $0.006 | $0.50 | 1,048,576 |
| OpenInference | open-inference/fp4 | fp4 | $0.0175 | $0.70 | 1,048,576 |
| Morph | morph/fp8 | fp8 | $0.022 | $0.40 | 1,048,576 |
| PrimeIntellect | primeintellect | Not stated | $0.039 | $1.20 | 1,048,576 |
| Wafer | wafer/us | mxfp4 | $0.051 | $0.567 | 1,048,576 |
| InferenceNet | inference-net/fp8 | fp8 | $0.103 | $0.60 | 1,040,000 |
| InferenceNet | inference-net/us | fp8 | $0.103 | $0.60 | 1,040,000 |
| DeepInfra | deepinfra/fp8/flex | fp8 | $0.112 | $0.336 | 1,048,576 |
| Reka | reka | Not stated | $0.12 | $0.96 | 1,048,576 |
| Mancer 2 | mancer/fp8 | fp8 | $0.125 | $0.50 | 1,048,576 |
| CoreWeave | coreweave/fp8 | fp8 | $0.13 | $0.65 | 1,048,576 |
| AtlasCloud | atlas-cloud/fp8 | fp8 | $0.135 | $0.54 | 1,048,576 |
| DeepInfra | deepinfra/fp8 | fp8 | $0.14 | $0.42 | 1,048,576 |
| StreamLake | streamlake/fp8 | fp8 | $0.147 | $0.588 | 1,024,000 |
| Alibaba | alibaba | Not stated | $0.15 | $0.60 | 1,000,000 |
| GMICloud | gmicloud/fp8 | fp8 | $0.18 | $0.72 | 1,048,575 |
| Wafer | wafer/mxfp4 | mxfp4 | $0.19 | $0.65 | 1,048,576 |
| Novita | novita/fp8 | fp8 | $0.195 | $0.78 | 1,048,576 |
| DeepInfra | deepinfra/fp8/priority | fp8 | $0.21 | $0.63 | 1,048,576 |
| Fireworks | fireworks/spot | Not stated | $0.21 | $0.84 | 1,048,576 |
| Phala | phala | Not stated | $0.21 | $0.84 | 1,048,576 |
| DigitalOcean | digitalocean | Not stated | $0.225 | $0.90 | 1,048,576 |
| Makora | makora/fp8 | fp8 | $0.26 | $1.17 | 1,048,576 |
| Crusoe | crusoe/fp8 | fp8 | $0.29 | $1.20 | 1,048,576 |
| Relace | relace/fast | fp4 | $0.30 | $0.90 | 1,048,576 |
| Baidu | baidu/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 |
| BaseTen | baseten | Not stated | $0.30 | $1.20 | 1,048,576 |
| BaseTen | baseten/us | Not stated | $0.30 | $1.20 | 1,048,576 |
| Cohere | cohere/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 |
| Fireworks | fireworks | Not stated | $0.30 | $1.20 | 1,048,576 |
google-vertex/global | Not stated | $0.30 | $1.20 | 1,048,576 | |
| Modal | modal | Not stated | $0.30 | $1.20 | 1,048,576 |
| Nebius | nebius/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 |
| Parasail | parasail/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.30 | $1.20 | 1,048,576 |
| Together | together | Not stated | $0.30 | $1.20 | 1,048,576 |
| Venice | venice/fp8 | fp8 | $0.30 | $1.20 | 1,000,000 |
| Fireworks | fireworks/us | Not stated | $0.45 | $1.80 | 1,048,576 |
| Parasail | parasail/fast | fp8 | $0.45 | $1.80 | 1,048,576 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
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 |
|---|---|---|---|---|
| Hosted by BytePlusreasoning: off110 answers on 22 dates · 100 % answered | 1.39 srange 1.17–4.33 s · slow 10 %: 1.67 s Observed | 125 tokens/srange 72.0–178 · slowest 10 %: 105 tokens/s | $0.000184range $0.000181–$0.000185 Calculated | 0for 64 visible |
United Kingdom · ObservedCollecting0 test requests so far
Germany · ObservedCollecting0 test requests so far
Canada · ObservedCollecting0 test requests so far
Australia · ObservedCollecting0 test requests so far
- 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
Figures the provider publishes (6)
| Benchmark | Provider's figure | Where the provider says it |
|---|---|---|
| GPQA Diamond | 90.9 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · Hugging Faceread 17 Oct 2026 |
| Humanity's Last Exam (HLE) | 36.8 (39.1†) Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · Hugging Faceread 17 Oct 2026 |
| Humanity's Last Exam (HLE), with tools | 63.9 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · Hugging Faceread 17 Oct 2026 |
| Terminal-Bench 2.1 | 90.6 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · Hugging Faceread 17 Oct 2026 |
| Terminal-Bench 4.0 | 31.2 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · Hugging Faceread 17 Oct 2026 |
| DeepSWE v1.1 | 74.2 Stated by the provider | Results table in deepseek-ai/DeepSeek-V4.1-Flash · 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 the provider's price (Unknown) | Through OpenRouter ($0.051 / $0.567) |
|---|---|---|
| 1,000 chat replies | Unknown | $0.22 |
| Summarizing 100 documents | Unknown | $0.04 |
| A day of coding assistant use | Unknown | $0.15 |
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.
Newer snapshot. The API name deepseek-flash now serves DeepSeek: DeepSeek V4.1 Flash 1017 (provider’s page). This page keeps the earlier snapshot 0910 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
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does DeepSeek V4.1 Flash cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.02 per 1M tokens | Published | |
| How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter? | $0.57 per 1M tokens | Published | |
| What is the context window of DeepSeek V4.1 Flash on OpenRouter, in tokens? | 1,048,576 tokens | Published | |
| What is the maximum output length of DeepSeek V4.1 Flash on OpenRouter, in tokens? | 943,718 tokens | Published |
History
- — $0.05 per 1M tokens → $0.05 per 1M tokens Confirmed by the check on 8 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.
- — $0.50 per 1M tokens → $0.57 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter?) Confirmed by the check on 8 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 → $0.02 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 5 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.
- — $0.42 per 1M tokens → $0.50 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter?) Confirmed by the check on 30 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.
- — $0.0042 per 1M tokens → $0.0060 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 30 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.
- — $0.14 per 1M tokens → $0.05 per 1M tokens Confirmed by the check on 30 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.
- — $0.02 per 1M tokens → $0.14 per 1M tokens Confirmed by the check on 28 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.
- — $1.00 per 1M tokens → $0.42 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter?) Confirmed by the check on 28 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.
- — $0.04 per 1M tokens → $0.02 per 1M tokens Confirmed by the check on 25 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.
- — $0.14 per 1M tokens → $1.00 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter?) Confirmed by the check on 25 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.
- — $0.64 per 1M tokens → $0.14 per 1M tokens (How much does DeepSeek V4.1 Flash cost per 1M output tokens on OpenRouter?) Confirmed by the check on 18 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.
- — First check: $0.04 per 1M tokens
- Short-lived or unconfirmed moves are not shown as changes.
The source record lists $0.000000051 per token ($0.05 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.000000051"
Latest briefings 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 V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
- 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 — 113 records for 5 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.05 per 1M tokens | Published |
| 8 Nov 2026 | $0.05 per 1M tokens | Published |
| 7 Nov 2026 | $0.05 per 1M tokens | Published |
| 6 Nov 2026 | $0.05 per 1M tokens | Published |
| 5 Nov 2026 | $0.05 per 1M tokens | Published |
| 4 Nov 2026 | $0.05 per 1M tokens | Published |
| 3 Nov 2026 | $0.05 per 1M tokens | Published |
| 2 Nov 2026 | $0.05 per 1M tokens | Published |
| 1 Nov 2026 | $0.05 per 1M tokens | Published |
| 31 Oct 2026 | $0.05 per 1M tokens | Published |
| 30 Oct 2026 | $0.05 per 1M tokens | Published |
| 29 Oct 2026 | $0.05 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.02 per 1M tokens | Published |
| 8 Nov 2026 | $0.02 per 1M tokens | Published |
| 7 Nov 2026 | $0.02 per 1M tokens | Published |
| 6 Nov 2026 | $0.02 per 1M tokens | Published |
| 5 Nov 2026 | $0.02 per 1M tokens | Published |
| 4 Nov 2026 | $0.02 per 1M tokens | Published |
| 3 Nov 2026 | $0.0060 per 1M tokens | Published |
| 2 Nov 2026 | $0.0060 per 1M tokens | Published |
| 1 Nov 2026 | $0.0060 per 1M tokens | Published |
| 31 Oct 2026 | $0.0060 per 1M tokens | Published |
| 30 Oct 2026 | $0.0060 per 1M tokens | Published |
| 29 Oct 2026 | $0.0060 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.57 per 1M tokens | Published |
| 8 Nov 2026 | $0.57 per 1M tokens | Published |
| 7 Nov 2026 | $0.57 per 1M tokens | Published |
| 6 Nov 2026 | $0.50 per 1M tokens | Published |
| 5 Nov 2026 | $0.50 per 1M tokens | Published |
| 4 Nov 2026 | $0.50 per 1M tokens | Published |
| 3 Nov 2026 | $0.50 per 1M tokens | Published |
| 2 Nov 2026 | $0.50 per 1M tokens | Published |
| 1 Nov 2026 | $0.50 per 1M tokens | Published |
| 31 Oct 2026 | $0.50 per 1M tokens | Published |
| 30 Oct 2026 | $0.50 per 1M tokens | Published |
| 29 Oct 2026 | $0.50 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 |
| 1 Nov 2026 | 1,048,576 tokens | Published |
| 31 Oct 2026 | 1,048,576 tokens | Published |
| 30 Oct 2026 | 1,048,576 tokens | Published |
| 29 Oct 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 |
| 1 Nov 2026 | 943,718 tokens | Published |
| 31 Oct 2026 | 943,718 tokens | Published |
| 30 Oct 2026 | 943,718 tokens | Published |
| 29 Oct 2026 | 943,718 tokens | Published |
Showing the latest 60 of 113 records; the full history is in data.json and data.csv.