DeepSeek V4 Flash 0731 API Pricing

DeepSeek V4 Flash 0731 API pricing: $0.0434 per 1M tokens for input and $0.30 per 1M tokens for output, from OpenRouter. Published Last checked · Source (data) · Methodology

OpenRouter: Amount worked out from the source page: $0.04 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.

Data as of9 Nov 2026Prices checked 9 Nov 2026 · test requests to 8 Nov 2026Data & API
Price changed 8 Nov 2026. input $0.059 → $0.0434 (−26.4 %) per 1M tokens on OpenRouter. Confirmed by a later check on 9 Nov 2026.

Prices USD per 1M tokens, as listed

  • $0.0434–$0.44Input per 1M tokens, through OpenRouter, across 30 endpoints Published
  • $0.14–$1.32Output per 1M tokens, through OpenRouter, across 30 endpoints Published
  • $0.048Batch input per 1M tokens, through OpenRouter Published

OpenRouter listing $0.0434 / $0.30 per 1M tokens: listing differs from 29 of 30 endpoints read on 9 Nov 2026.

All prices by channel
Price per 1M tokensProvider directThrough OpenRouterPrevious prices by channel
Input—$0.0434–$0.44 Publishedacross 30 endpoints; listing $0.0434: listing differs from 29 of 30 endpointsOpenRouter: $0.059 until 8 Nov 2026
Output—$0.14–$1.32 Publishedacross 30 endpoints; listing $0.30: listing differs from 29 of 30 endpointsOpenRouter: $0.238 until 3 Nov 2026
Cached input · read—$0.035 Published—
Batch · input / output—$0.048 / $0.144 Published—

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

16 Oct 2026$0.0154 → $0.0434 (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 $0.0434 · Wafer (wafer/us); output $0.14 · Relace (relace/fp4)

Unpinned range: input $0.0434–$0.44, output $0.14–$1.32 across 30 endpoints of 26 providers (listing shows $0.14 / $0.30).

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 $0.059 / $0.30 → $0.14 / $0.30 (input +137%, output 0%).
  • StreamLake (streamlake/fp8): $0.088 / $0.264 → $0.132 / $0.396 (input +50%, output +50%).
  • Baidu (baidu/fp8): $0.04444 / $0.13332 → $0.44 / $1.32 (input +890%, output +890%).
  • PrimeIntellect (primeintellect/fp4): $0.09 / $0.23 → $0.44 / $1.32 (input +389%, output +474%).
  • Lowest-priced endpoint for the workload: Wafer (wafer/us) at $0.47 per 1,000 tasks, before Baidu (baidu/fp8) at $0.39.

Observed unpinned cost: 18 short requests sent without a pinned provider on 26 Oct 2026 and 27 Oct 2026, 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 modeRequestsDatesServed byChargedListing price for the same tokensCharged / listingLowest-priced endpoint answered
Default (no provider field)626 Oct 2026 and 27 Oct 20266 of 6 Sail Research (sail-research/us)$0.000073$0.000500.15×0 of 6
:floor626 Oct 2026 and 27 Oct 20263 of 6 Relace (relace/fp4), 2 of 6 DeepInfra (deepinfra/fp8), 1 of 6 Reka (reka)$0.000064$0.000500.13×3 of 6
:nitro626 Oct 2026 and 27 Oct 20262 of 6 BaseTen (baseten/fp8), 2 of 6 Venice (venice), 2 of 6 Wafer (wafer/fast)$0.00012$0.000490.24×0 of 6

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 Wafer (wafer/us):

{"provider": {"order": ["wafer/us"], "allow_fallbacks": false}}

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 (30), by input price
ProviderEndpoint tagPrecisionInputOutputContext, tokens
Waferwafer/usnvfp4$0.0434$0.301,048,576
DeepInfradeepinfra/fp8fp8$0.06$0.181,048,576
Relacerelace/fp4fp4$0.07$0.141,048,576
Waferwafer/fastnvfp4$0.10$0.231,048,576
RekarekaNot stated$0.10$0.28262,144
DigitalOceandigitaloceanNot stated$0.119$0.2381,048,576
BaseTenbaseten/fp32fp32$0.13$0.261,048,576
BaseTenbaseten/fp8fp8$0.13$0.261,048,576
VeniceveniceNot stated$0.13$0.261,000,000
CoreWeavecoreweave/fp8fp8$0.13$0.27262,144
Inceptroninceptron/fp4fp4$0.13$0.4951,048,576
StreamLakestreamlake/fp8fp8$0.132$0.3961,024,000
Coherecohere/fp8fp8$0.14$0.281,048,576
Nebiusnebius/fp8fp8$0.14$0.281,048,576
Parasailparasail/fp8fp8$0.14$0.281,048,576
Morphmorph/bf16bf16$0.142$0.401,048,576
Sail Researchsail-research/fp4fp4$0.15$0.301,048,576
Sail Researchsail-research/usfp4$0.15$0.301,048,576
Mancer 2mancer/fp8fp8$0.15$0.501,048,576
SiliconFlowsiliconflow/fp8fp8$0.22$0.661,048,576
GMICloudgmicloud/fp8fp8$0.286$0.8581,048,575
AlibabaalibabaNot stated$0.352$1.0561,000,000
Alibabaalibaba/us-east-1Not stated$0.374$1.1221,000,000
Novitanovita/fp8fp8$0.4092$1.22761,048,576
AtlasCloudatlas-cloud/fp4fp4$0.44$1.321,048,576
Baidubaidu/fp8fp8$0.44$1.321,048,576
Chuteschutes/fp8fp8$0.44$1.321,048,576
CloudflarecloudflareNot stated$0.44$1.321,048,576
PhalaphalaNot stated$0.44$1.321,048,576
PrimeIntellectprimeintellect/fp4fp4$0.44$1.321,048,576

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

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 Flash 0731 cost per 1M cache-read tokens (cache hits) on OpenRouter?$0.04 per 1M tokensPublished
How much does DeepSeek V4 Flash 0731 cost per 1M output tokens on OpenRouter?$0.30 per 1M tokensPublished
What is the context window of DeepSeek V4 Flash 0731 on OpenRouter, in tokens?1,048,576 tokensPublished
What is the maximum output length of DeepSeek V4 Flash 0731 on OpenRouter, in tokens?943,718 tokensPublished

History

  1. — $0.06 per 1M tokens → $0.04 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.
  2. — $0.02 per 1M tokens → $0.04 per 1M tokens (How much does DeepSeek V4 Flash 0731 cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 4 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. — $0.12 per 1M tokens → $0.06 per 1M tokens Confirmed by the check on 4 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. — $0.24 per 1M tokens → $0.30 per 1M tokens (How much does DeepSeek V4 Flash 0731 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 4 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.
  5. — $1.32 per 1M tokens → $0.24 per 1M tokens (How much does DeepSeek V4 Flash 0731 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.
  6. — $0.44 per 1M tokens → $0.12 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.
  7. — 131,072 tokens → 943,718 tokens (What is the maximum output length of DeepSeek V4 Flash 0731 on OpenRouter, in tokens?) Confirmed by the check on 28 Oct 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
  8. — $1.28 per 1M tokens → $1.32 per 1M tokens (How much does DeepSeek V4 Flash 0731 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 21 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.
  9. — $0.02 per 1M tokens → $0.44 per 1M tokens Confirmed by the check on 21 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.
  10. — 943,718 tokens → 131,072 tokens (What is the maximum output length of DeepSeek V4 Flash 0731 on OpenRouter, in tokens?) Confirmed by the check on 21 Oct 2026. What this means for you: The figure you would rely on has moved; check the evidence before relying on the old one.
  11. — First check: $0.02 per 1M tokens
  12. Short-lived or unconfirmed moves are not shown as changes.

The source record lists $0.000000043 per token ($0.04 per 1M tokens), fetched on 9 Nov 2026.

The source record, as published
"prompt":"0.0000000434"
What the source says · openrouter.ai

Latest briefings each price change recalculated as a task cost

  1. DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
  2. 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 %)
  3. MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)

All briefings

Record history — 113 records for 5 questions
Last record
Shown in
the United States
How much does DeepSeek V4 Flash 0731 cost per 1M input tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.04 per 1M tokensPublished
8 Nov 2026$0.04 per 1M tokensPublished
7 Nov 2026$0.06 per 1M tokensPublished
6 Nov 2026$0.06 per 1M tokensPublished
5 Nov 2026$0.06 per 1M tokensPublished
4 Nov 2026$0.06 per 1M tokensPublished
3 Nov 2026$0.06 per 1M tokensPublished
2 Nov 2026$0.12 per 1M tokensPublished
1 Nov 2026$0.12 per 1M tokensPublished
31 Oct 2026$0.12 per 1M tokensPublished
30 Oct 2026$0.12 per 1M tokensPublished
29 Oct 2026$0.12 per 1M tokensPublished
How much does DeepSeek V4 Flash 0731 cost per 1M cache-read tokens (cache hits) on OpenRouter?
TimeValueStatus
9 Nov 2026$0.04 per 1M tokensPublished
8 Nov 2026$0.04 per 1M tokensPublished
7 Nov 2026$0.04 per 1M tokensPublished
6 Nov 2026$0.04 per 1M tokensPublished
5 Nov 2026$0.04 per 1M tokensPublished
4 Nov 2026$0.04 per 1M tokensPublished
3 Nov 2026$0.04 per 1M tokensPublished
2 Nov 2026$0.02 per 1M tokensPublished
1 Nov 2026$0.02 per 1M tokensPublished
31 Oct 2026$0.02 per 1M tokensPublished
30 Oct 2026$0.02 per 1M tokensPublished
29 Oct 2026$0.02 per 1M tokensPublished
How much does DeepSeek V4 Flash 0731 cost per 1M output tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.30 per 1M tokensPublished
8 Nov 2026$0.30 per 1M tokensPublished
7 Nov 2026$0.30 per 1M tokensPublished
6 Nov 2026$0.30 per 1M tokensPublished
5 Nov 2026$0.30 per 1M tokensPublished
4 Nov 2026$0.30 per 1M tokensPublished
3 Nov 2026$0.30 per 1M tokensPublished
2 Nov 2026$0.24 per 1M tokensPublished
1 Nov 2026$0.24 per 1M tokensPublished
31 Oct 2026$0.24 per 1M tokensPublished
30 Oct 2026$0.24 per 1M tokensPublished
29 Oct 2026$0.24 per 1M tokensPublished
What is the context window of DeepSeek V4 Flash 0731 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 Flash 0731 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026943,718 tokensPublished
8 Nov 2026943,718 tokensPublished
7 Nov 2026943,718 tokensPublished
6 Nov 2026943,718 tokensPublished
5 Nov 2026943,718 tokensPublished
4 Nov 2026943,718 tokensPublished
3 Nov 2026943,718 tokensPublished
2 Nov 2026943,718 tokensPublished
1 Nov 2026943,718 tokensPublished
31 Oct 2026943,718 tokensPublished
30 Oct 2026943,718 tokensPublished
29 Oct 2026943,718 tokensPublished

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