InferIndex
Language, English, EN
Account

ModelsDeepSeekDeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-07311M context Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.233
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.793
Offers
130
Providers
55

Cheapest right now

$0.083 blended / 1M tokens

No change7D
in
$0.04
out
$0.21
Cached input
$0.02
Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

DeepSeek V4 Flash 0731 costs from $0.083 per million tokens (at a 3:1 input:output mix): the cheapest of 36 comparable offers, at Boundless, checked on ; 130 offers are listed.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (94)

  • $0.078 · NanoGPT via NanoGPT · not selected as cheapest: its price changes often
  • $0.081 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.088 · Relace via Kilo Gateway · cannot be designated the cheapest
  • $0.088 · Relace via OpenRouter · cannot be designated the cheapest
  • $0.088 · Baidu via OpenRouter · cannot be designated the cheapest
  • $0.09 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.09 · DeepInfra via Hugging Face · another route of the same provider
  • $0.09 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.09 · DeepInfra via Vercel AI Gateway · another route of the same provider
  • $0.09 · DeepInfra via OpenRouter · cannot be designated the cheapest
  • $0.095 · Runware via Requesty · another route of the same provider
  • $0.105 · DeepInfra via LLM Gateway · another route of the same provider
  • $0.113 · DeepInfra via Requesty · another route of the same provider
  • $0.119 · Wafer via Kilo Gateway · cannot be designated the cheapest
  • $0.119 · Wafer via OpenRouter · cannot be designated the cheapest
  • $0.121 · Wafer via Kilo Gateway · cannot be designated the cheapest
  • $0.121 · Wafer via OpenRouter · cannot be designated the cheapest
  • $0.132 · StreamLake via OpenRouter · cannot be designated the cheapest
  • $0.135 · DeepInfra · priority tier
  • $0.145 · Reka via Kilo Gateway · cannot be designated the cheapest
  • $0.145 · Reka via OpenRouter · cannot be designated the cheapest
  • $0.149 · DigitalOcean via Kilo Gateway · cannot be designated the cheapest
  • $0.149 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.149 · FlexAI via Eden AI · cannot be designated the cheapest
  • $0.149 · DigitalOcean via OpenRouter · cannot be designated the cheapest
  • $0.156 · io.net · cannot be designated the cheapest
  • $0.163 · BaseTen via Kilo Gateway · cannot be designated the cheapest
  • $0.163 · BaseTen via Kilo Gateway · cannot be designated the cheapest
  • $0.163 · BaseTen via Vercel AI Gateway · another route of the same provider
  • $0.163 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.163 · BaseTen via OpenRouter · cannot be designated the cheapest
  • $0.163 · Venice via OpenRouter · cannot be designated the cheapest
  • $0.163 · BaseTen via OpenRouter · cannot be designated the cheapest
  • $0.166 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.168 · CoreWeave via Kilo Gateway · cannot be designated the cheapest
  • $0.168 · Inceptron via Vercel AI Gateway · another route of the same provider
  • $0.168 · CoreWeave via OpenRouter · cannot be designated the cheapest
  • $0.175 · Canopywave via LLM API · cannot be designated the cheapest
  • $0.175 · Cohere via Kilo Gateway · cannot be designated the cheapest
  • $0.175 · Nebius via Eden AI · cannot be designated the cheapest
  • $0.175 · Parasail via Kilo Gateway · cannot be designated the cheapest
  • $0.175 · Glama via Glama · cannot be designated the cheapest
  • $0.175 · Novita via Requesty · another route of the same provider
  • $0.175 · Together via LLM Gateway · cannot be designated the cheapest
  • $0.175 · Cohere via OpenRouter · cannot be designated the cheapest
  • $0.175 · Parasail via OpenRouter · cannot be designated the cheapest
  • $0.188 · Sail Research via Kilo Gateway · cannot be designated the cheapest
  • $0.188 · Sail Research via Kilo Gateway · cannot be designated the cheapest
  • $0.188 · Sail Research via OpenRouter · cannot be designated the cheapest
  • $0.188 · Sail Research via OpenRouter · cannot be designated the cheapest
  • $0.215 · Alibaba via Eden AI · cannot be designated the cheapest
  • $0.215 · Greenpt via Eden AI · cannot be designated the cheapest
  • $0.221 · Inceptron via Kilo Gateway · cannot be designated the cheapest
  • $0.221 · Inceptron via OpenRouter · cannot be designated the cheapest
  • $0.25 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.263 · TensorX via Eden AI · cannot be designated the cheapest
  • $0.264 · Alibaba via Kilo Gateway · cannot be designated the cheapest
  • $0.264 · Alibaba via OpenRouter · cannot be designated the cheapest
  • $0.281 · Alibaba via Kilo Gateway · cannot be designated the cheapest
  • $0.281 · Alibaba via OpenRouter · cannot be designated the cheapest
  • $0.30 · Mancer 2 via Kilo Gateway · cannot be designated the cheapest
  • $0.30 · Mancer 2 via OpenRouter · cannot be designated the cheapest
  • $0.326 · Martian via Martian · cannot be designated the cheapest
  • $0.33 · Alibaba via LLM API · cannot be designated the cheapest
  • $0.33 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $0.33 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.33 · Fireworks via LLM Gateway · cannot be designated the cheapest
  • $0.33 · SiliconFlow via OpenRouter · cannot be designated the cheapest
  • $0.338 · UCloud · cannot be designated the cheapest
  • $0.35 · Sference via Eden AI · cannot be designated the cheapest
  • $0.362 · UCloud · cannot be designated the cheapest
  • $0.429 · GMICloud via OpenRouter · cannot be designated the cheapest
  • $0.438 · Venice · priority tier
  • $0.545 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.559 · Scaleway via Eden AI · cannot be designated the cheapest
  • $0.614 · Novita via OpenRouter · cannot be designated the cheapest
  • $0.66 · Novita · another route of the same provider
  • $0.66 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · Baidu via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · Cloudflare via Eden AI · cannot be designated the cheapest
  • $0.66 · Cloudflare via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · Novita via Hugging Face · another route of the same provider
  • $0.66 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · Novita via LLM API · cannot be designated the cheapest
  • $0.66 · Novita via Vercel AI Gateway · another route of the same provider
  • $0.66 · Phala via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · StreamLake via Kilo Gateway · cannot be designated the cheapest
  • $0.66 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
  • $0.66 · Charm Hyper via Charm Hyper · cannot be designated the cheapest
  • $0.66 · Cloudflare via LLM Gateway · another route of the same provider
  • $0.66 · AtlasCloud via OpenRouter · cannot be designated the cheapest
  • $0.66 · Cloudflare via OpenRouter · cannot be designated the cheapest
  • $0.66 · Phala via OpenRouter · cannot be designated the cheapest

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

DeepInfra

directYou buy access straight from the company that runs the model on its servers. · fp8 · 1M

$0.09 blended / 1M tokens

in
$0.06
out
$0.18
Cached input
$0.015
Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.066, StreamLake–
2026-10-03$0.066, StreamLake–
2026-10-04$0.066, StreamLake–
2026-10-05$0.066, StreamLake–
2026-10-06$0.066, StreamLake–
2026-10-07$0.066, StreamLake–
2026-10-08$0.066, StreamLake–
2026-10-09$0.066, StreamLake–
2026-10-10$0.0054, OpenInference–
2026-10-11$0.078, NanoGPT–
2026-10-12$0.078, NanoGPT–
2026-10-13$0.078, NanoGPT–
2026-10-14$0.078, NanoGPT–
2026-10-15$0.078, NanoGPT–
2026-10-16$0.078, NanoGPT–
2026-10-17$0.078, NanoGPT–
2026-10-18$0.078, NanoGPT–
2026-10-19$0.083, Boundless–
2026-10-20$0.083, Boundless–
2026-10-21$0.083, Boundless–
2026-10-22$0.083, Boundless–
2026-10-23$0.083, Boundless–
2026-10-24$0.083, Boundless–
2026-10-25$0.083, Boundless–
2026-10-26$0.083, Boundless–
2026-10-27$0.083, Boundless–
2026-10-28$0.074, Relace–
2026-10-29$0.074, Relace–
2026-10-30$0.083, Boundless–
2026-10-31$0.083, Boundless–

Cheapest offerPromotional price

Offers

The 25 cheapest of 130 offers

Offers for DeepSeek V4 Flash 0731, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 NanoGPT 0.05  0.16  0.078 – 1M Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer existsPrice changes often: 10 price changes in 7 days. Over that period: input $0.044 – $0.05, output $0.133 – $0.16 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at NanoGPT (opens in a new tab)
2 Nous Portal 0.054 0.162 0.081 – 1M Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
3 Boundlessvia Vercel AI Gateway 0.04  0.21  0.083 – 1M
Go to offer at Vercel AI Gateway (opens in a new tab)
4 Relacevia Kilo Gateway 0.07  0.14  0.088 fp4 1M Unverified. No public page for this offer: listed, not designated cheapestPrice drop observed: The blended price is 73% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 52 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $0.195 per million tokens. An offer whose price changes this often is not selected as the cheapest.
: Kilo Gateway (opens in a new tab). No public price page for this model
5 Relacevia Vercel AI Gateway 0.07  0.14  0.088 fp4 1M Price drop observed: The blended price is 76% lower than before this drop; possibly temporary. · Price drop observed since Oct 27, 2026Price changes often: 40 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $1.28 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at Vercel AI Gateway (opens in a new tab)
6 Relacevia OpenRouter 0.07  0.14  0.088 fp4 1M Price drop observed: The blended price is 73% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 170 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $0.195 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
7 Baiduvia OpenRouter 0.059 0.177 promo: Promotion announced by OpenRouter · −87% vs its usual price · end date not published0.088 fp8 1M Price changes often: 16 price changes in 7 days. Over that period: input $0.044 – $0.44, output $0.133 – $1.32 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
8 DeepInfra 0.06  0.18  0.09  fp8 1M United States
Go to offer at DeepInfra (opens in a new tab)
9 DeepInfravia Eden AI 0.06  0.18  0.09  fp8 1M United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
10 DeepInfravia Hugging Face 0.06  0.18  0.09  fp8 1M United States
See pricing at Hugging Face (opens in a new tab)
11 DeepInfravia Kilo Gateway 0.06  0.18  0.09  fp8 1M United States Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
12 DeepInfravia Vercel AI Gateway 0.06  0.18  0.09  fp8 1M United States
Go to offer at Vercel AI Gateway (opens in a new tab)
13 DeepInfravia OpenRouter 0.06  0.18  0.09  fp8 1M United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
14 Runwarevia Vercel AI Gateway 0.076 0.153 0.095 fp8 1M
Go to offer at Vercel AI Gateway (opens in a new tab)
15 Runwarevia Requesty 0.076 0.153 0.095 – 1M Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
16 DeepInfravia LLM Gateway 0.08  0.18  0.105 fp8 – United States Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer at LLM Gateway (opens in a new tab)
17 DeepInfravia Requesty 0.09  0.18  0.113 fp8 1M United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
18 Sail Researchvia Requesty 0.09  0.18  0.113 fp4 1M Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
19 Wafervia Kilo Gateway 0.058 0.30  0.119 fp4 1M United States Unverified. No public page for this offer: listed, not designated cheapestPrice changes often: 34 price changes in 7 days. Over that period: input $0.03 – $0.058, output $0.30 per million tokens. An offer whose price changes this often is not selected as the cheapest.
: Kilo Gateway (opens in a new tab). No public price page for this model
20 Wafervia OpenRouter 0.058 0.30  0.119 fp4 1M United States Price changes often: 130 price changes in 7 days. Over that period: input $0.03 – $0.059, output $0.30 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
21 Wafervia Kilo Gateway 0.085 0.23  0.121 fp4 1M Unverified. No public page for this offer: listed, not designated cheapestPrice drop observed: The blended price is 37% lower than before this drop; possibly temporary. · Price drop observed since Oct 21, 2026Price changes often: 47 price changes in 7 days. Over that period: input $0.085 – $0.14, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.+1Priority tier: A different service tier, with its own speed and availability conditions.
: Kilo Gateway (opens in a new tab). No public price page for this model
22 Wafervia Vercel AI Gateway 0.085 0.23  0.121 – 1M Price drop observed: The blended price is 68% lower than before this drop; possibly temporary. · Price drop observed since Oct 9, 2026Price changes often: 44 price changes in 7 days. Over that period: input $0.085 – $0.14, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at Vercel AI Gateway (opens in a new tab)
23 Wafervia OpenRouter 0.085 0.23  0.121 fp4 1M Price drop observed: The blended price is 51% lower than before this drop; possibly temporary. · Price drop observed since Oct 26, 2026Price changes often: 79 price changes in 7 days. Over that period: input $0.085 – $0.25, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.Priority tier: A different service tier, with its own speed and availability conditions.+1Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
24 DigitalOceanvia Vercel AI Gateway 0.08  0.252 0.123 – 1M
Go to offer at Vercel AI Gateway (opens in a new tab)
25 StreamLakevia OpenRouter 0.088 0.264 0.132 fp8 1M Price drop observed: The blended price is 80% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 31, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

  • NanoGPT

    $0.078

    NanoGPT

    in
    $0.05 
    out
    $0.16 
    Precision
    –
    Context
    1M

    No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer existsPrice changes often: 10 price changes in 7 days. Over that period: input $0.044 – $0.05, output $0.133 – $0.16 per million tokens. An offer whose price changes this often is not selected as the cheapest.

    Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

  • Nous Portal

    $0.081

    Nous Portal

    in
    $0.054
    out
    $0.162
    Precision
    –
    Context
    1M

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal

  • Boundless

    $0.083

    Vercel AI Gateway

    in
    $0.04 
    out
    $0.21 
    Precision
    –
    Context
    1M

    Training terms not published

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • Relace

    $0.088

    Kilo Gateway

    in
    $0.07 
    out
    $0.14 
    Precision
    fp4
    Context
    1M

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapestPrice drop observed: The blended price is 73% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 52 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $0.195 per million tokens. An offer whose price changes this often is not selected as the cheapest.

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Relace

    $0.088

    Vercel AI Gateway

    in
    $0.07 
    out
    $0.14 
    Precision
    fp4
    Context
    1M

    Training terms not publishedPrice drop observed: The blended price is 76% lower than before this drop; possibly temporary. · Price drop observed since Oct 27, 2026Price changes often: 40 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $1.28 per million tokens. An offer whose price changes this often is not selected as the cheapest.

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • Relace

    $0.088

    OpenRouter

    in
    $0.07 
    out
    $0.14 
    Precision
    fp4
    Context
    1M

    Training terms not publishedPrice drop observed: The blended price is 73% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 170 price changes in 7 days. Over that period: input $0.031 – $0.07, output $0.134 – $0.195 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Baidu

    promo: Promotion announced by OpenRouter · −87% vs its usual price · end date not published$0.088

    OpenRouter

    in
    $0.059
    out
    $0.177
    Precision
    fp8
    Context
    1M

    Training terms not publishedPrice changes often: 16 price changes in 7 days. Over that period: input $0.044 – $0.44, output $0.133 – $1.32 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • DeepInfra

    $0.09

    direct

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    No training on promptsUnited States

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • DeepInfra

    $0.09

    Eden AI

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.09

    Hugging Face

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    No training on promptsUnited States

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • DeepInfra

    $0.09

    Kilo Gateway

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    Training terms not publishedUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.09

    Vercel AI Gateway

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    No training on promptsUnited States

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • DeepInfra

    $0.09

    OpenRouter

    in
    $0.06 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    No training on promptsUnited StatesFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Runware

    $0.095

    Vercel AI Gateway

    in
    $0.076
    out
    $0.153
    Precision
    fp8
    Context
    1M

    Training terms not published

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • Runware

    $0.095

    Requesty

    in
    $0.076
    out
    $0.153
    Precision
    –
    Context
    1M

    Prompts may be used for trainingFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • DeepInfra

    $0.105

    LLM Gateway

    in
    $0.08 
    out
    $0.18 
    Precision
    fp8
    Context
    –

    No training on promptsUnited StatesFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

    Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway

  • DeepInfra

    $0.113

    Requesty

    in
    $0.09 
    out
    $0.18 
    Precision
    fp8
    Context
    1M

    Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • Sail Research

    $0.113

    Requesty

    in
    $0.09 
    out
    $0.18 
    Precision
    fp4
    Context
    1M

    Prompts may be used for trainingFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • Wafer

    $0.119

    Kilo Gateway

    in
    $0.058
    out
    $0.30 
    Precision
    fp4
    Context
    1M

    Training terms not publishedUnited StatesUnverified. No public page for this offer: listed, not designated cheapestPrice changes often: 34 price changes in 7 days. Over that period: input $0.03 – $0.058, output $0.30 per million tokens. An offer whose price changes this often is not selected as the cheapest.

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Wafer

    $0.119

    OpenRouter

    in
    $0.058
    out
    $0.30 
    Precision
    fp4
    Context
    1M

    Training terms not publishedUnited StatesPrice changes often: 130 price changes in 7 days. Over that period: input $0.03 – $0.059, output $0.30 per million tokens. An offer whose price changes this often is not selected as the cheapest.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Wafer

    $0.121

    Kilo Gateway

    in
    $0.085
    out
    $0.23 
    Precision
    fp4
    Context
    1M

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapestPrice drop observed: The blended price is 37% lower than before this drop; possibly temporary. · Price drop observed since Oct 21, 2026Price changes often: 47 price changes in 7 days. Over that period: input $0.085 – $0.14, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.Priority tier: A different service tier, with its own speed and availability conditions.

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Wafer

    $0.121

    Vercel AI Gateway

    in
    $0.085
    out
    $0.23 
    Precision
    –
    Context
    1M

    Training terms not publishedPrice drop observed: The blended price is 68% lower than before this drop; possibly temporary. · Price drop observed since Oct 9, 2026Price changes often: 44 price changes in 7 days. Over that period: input $0.085 – $0.14, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • Wafer

    $0.121

    OpenRouter

    in
    $0.085
    out
    $0.23 
    Precision
    fp4
    Context
    1M

    Training terms not publishedPrice drop observed: The blended price is 51% lower than before this drop; possibly temporary. · Price drop observed since Oct 26, 2026Price changes often: 79 price changes in 7 days. Over that period: input $0.085 – $0.25, output $0.23 per million tokens. An offer whose price changes this often is not selected as the cheapest.Priority tier: A different service tier, with its own speed and availability conditions.Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • DigitalOcean

    $0.123

    Vercel AI Gateway

    in
    $0.08 
    out
    $0.252
    Precision
    –
    Context
    1M

    No training on prompts

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • StreamLake

    $0.132

    OpenRouter

    in
    $0.088
    out
    $0.264
    Precision
    fp8
    Context
    1M

    Training terms not publishedPrice drop observed: The blended price is 80% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 31, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at OpenRouter (opens in a new tab)via OpenRouter
Show all 130 offers

3 flex or batch offers hidden (lower priority, variable latency).

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Boundless$5.55per month
  2. DeepInfra$6.30per month+$0.75 vs the cheapest
  3. Relace$6.30per month+$0.75 vs the cheapest

Host it yourself instead? See the break-even

Compare DeepSeek V4 Flash 0731 with

Related models

More from DeepSeek

All DeepSeek models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=deepseek/deepseek-v4-flash-0731
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.