API PRICES

DeepSeek · DeepSeek-V4-Flash-0731

Provider prices, cheapest first

Browse all models

DeepSeek · DeepSeek-V4-Flash-0731 official price: not yet recorded. Cheapest inference provider: DeepInfra, input 0.06, output 0.18 USD per million tokens. Relays have only older quotes; the lowest is openoneapi.com, group "Chinese models [machine translation] (on site: 国模)" 0.02125 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 82 sites have comparable prices; 225 sites list this model.Relay blended price uses 75% input and 25% output.

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
DeepInfra0.060.180.015—USD / 1M tokens
Official source
OpenRouter · Aggregator0.00581.280.0058—USD / 1M tokens
Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

sites have comparable prices82225 sites list this model; approximately 50 operators
Older lowest input price (reference)0.0714285714286USD credits / 1M
Median of each provider’s lowest price0.5USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Older price
01aws.babyAsk or discussCollected:
View 2 plans
Alibaba Cloud selected special offers [machine translation]Group on site: 阿里云精选特惠
Name on site: deepseek-v4-flash-0731
Qwen3.8 k3 GLM5.2 DeepSeek V4 and other models at a 50% special offer; for high volume you can get a key or sub-account [machine translation]Original: Qwen3.8 k3 GLM5.2 DeepSeek V4 等模型 5折特惠 量大可以上key或子账户
0.07142857142860.1428571428572—0.08928571428575Full prices and sources
02wqdsjhaoai.siteAsk or discussCollected:
View 1 plans
coderapi
Name on site: deepseek-v4-flash-0731
0.10.40.0020.175Full prices and sources
03ainzy.netAsk or discussCollected:
View 2 plans
chinese-model-3
Name on site: deepseek-v4-flash-0731
Chinese models high cache group · 30% of official price | Chinese Models (DeepSeek / GLM / Kimi) · 30% of list [machine translation]Original: 国模高缓存组 · 官方价 3 折 | Chinese Models (DeepSeek / GLM / Kimi) · 30% of list
0.100000020.3600000720.001800000360.165000033Full prices and sources
04apiqd.comAsk or discussCollected:
View 1 plans
deepseek
Name on site: deepseek-v4-flash-0731
All latest models supported [machine translation]Original: 最新模型均支持
0.1050.3150.01050.1575Full prices and sources
05bikip.proAsk or discussCollected:
View 2 plans
jailb
jailbreak
0.110.330.003499999999980.165Full prices and sources
06gptapi.asiaAsk or discussCollected:
View 2 plans
2 more sites of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

default
Name on site: deepseek-v4-flash-0731
Default channel [machine translation]Original: 默认通道
0.1120.224—0.14Full prices and sources
07realmrouter.cnAsk or discussCollected:
View 2 plans
Chinese models [machine translation]Group on site: 国模
Name on site: deepseek-v4-flash-0731
Includes qwen glm kimi DeepSeek minimax [machine translation]Original: 内含 qwen glm kimi DeepSeek minimax
0.120.480.0240.21Full prices and sources
08openp.aiAsk or discussCollected:
View 2 plans
default
Name on site: deepseek-v4-flash-0731
Official API [machine translation]Original: 官方API
0.1250.250.0250.15625Full prices and sources
09new.ainat.qzz.ioAsk or discussCollected:
View 1 plans
Chinese models [machine translation]Group on site: 国模
Name on site: deepseek-v4-flash-0731
deepseek no cache [machine translation]Original: deepseek 无缓存
0.130.520.00260.2275Full prices and sources
10sheapi.topAsk or discussCollected:
View 1 plans
deepseek
Name on site: deepseek-v4-flash-0731
deepseek series models, in-house special-supply channel [machine translation]Original: deepseek系列模型,自研特供渠道
0.210.630.006999999999930.315Full prices and sources
11coderelay.cnAsk or discussCollected:
View 1 plans
DeepSeek
Name on site: deepseek-v4-flash-0731
0.31.20.0060.525Full prices and sources
12aiai.160219.xyzAsk or discussCollected:
View 1 plans
deepseek
Name on site: deepseek-v4-flash-0731
0.3360.9800000000001120.121999999999920.497000000000028Full prices and sources
13ccoo.aiAsk or discussCollected:
View 1 plans
Deepseek official [machine translation]Group on site: Deepseek 官方
Name on site: deepseek-v4-flash-0731
DeepSeek V4 Pro, V4 Flash and other models, strong in complex reasoning, Coding, Agent and cost efficiency [machine translation]Original: DeepSeek V4 Pro、V4 Flash 等模型,在复杂推理、Coding、Agent 与成本效率方面表现突出
0.33751.01250.01124999999988750.50625Full prices and sources
14api.llmgw.xyzAsk or discussCollected:
View 2 plans
gm-01
Name on site: deepseek-v4-flash-0731
0.361.080.011999999999880.54Full prices and sources
15555codex.xyzAsk or discussCollected:
View 1 plans
Chinese models [machine translation]Group on site: 国产模型
Name on site: deepseek-v4-flash-0731
Chinese models [machine translation]Original: 国产模型
0.391.170.012999999999870.585Full prices and sources
16pro.auroai.icuAsk or discussCollected:
View 1 plans
Chinese [machine translation]Group on site: 国
Name on site: deepseek-v4-flash-0731
Chinese [machine translation]Original: 国
0.41.60.010.7Full prices and sources
17dahlo.liveAsk or discussCollected:
View 1 plans
DeepSeek
Name on site: deepseek-v4-flash-0731
0.4040.8080.0079999999999920.505Full prices and sources
18api.apiyi.comAsk or discussCollected:
View 3 plans
1 more site of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

ClaudeCode
Name on site: deepseek-v4-flash-0731
ClaudeCode
0.4181.2540.0133760.627Full prices and sources
19airouter.cloudAsk or discussCollected:
View 1 plans
default
Name on site: deepseek-v4-flash-0731
Default group [machine translation]Original: 默认分组
0.441.320.013999999999920.66Full prices and sources
19api.gravitex.aiAsk or discussCollected:
View 1 plans
default
Name on site: deepseek-v4-flash-0731
Default group [machine translation]Original: 默认分组
0.441.320.039999999999960.66Full prices and sources
21ai.gpt666claude.topAsk or discussCollected:
View 1 plans
gm
Name on site: deepseek-v4-flash-0731
0.451.350.014999999999850.675Full prices and sources
21mzhcloud.comAsk or discussCollected:
View 1 plans
Chinese models [machine translation]Group on site: 国产模型
Name on site: deepseek-v4-flash-0731
ds low cache, includes deepseek, glm, kimi, mimo, hunyuan, qwen, Minimax, etc. [machine translation]Original: ds低缓存,包括deepseek、glm、kimi、mimo、hunyuan、qwen、Minimax等
0.451.350.014999999999850.675Full prices and sources
23api.ai-gaochao.cnAsk or discussCollected:
View 18 plans
guo_chan
Name on site: deepseek-v4-flash-0731
guo_chan
0.510.10.625Full prices and sources
23sg.uiuiapi.comAsk or discussCollected:
View 2 plans
🔥SSSvip special offer [machine translation]Group on site: 🔥SSSvip特惠
Name on site: deepseek-v4-flash-0731
🔥SSSvip limited-time special price | supports Deepseek/Gemini [machine translation]Original: 🔥SSSvip 限时特价 | 支持Deepseek/Gemini
0.51—0.625Full prices and sources
25aimoniker.topAsk or discussCollected:
View 3 plans
Chinese models perk [machine translation]Group on site: 国模福利
Name on site: deepseek-v4-flash-0731
Chinese models perk group, includes latest ds4.1f, glm5.3f, k3 and other models [machine translation]Original: 国模福利分组,包含最新的ds4.1f、glm5.3f、k3等模型
0.752.250.024999999999751.125Full prices and sources
Special groups · 3 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

  • zero-ratio group: 2 rows
  • test or debug group: 1 rows
  • api.wapq.cn · Perk [machine translation]Group on site: 福利 · deepseek-v4-flash-0731 · Input 0 / Output 0 USD credits / 1M
  • wqdsjhaoai.site · Free 1 yi (100 million) token daily, shared site-wide [machine translation]Group on site: 每日免费1亿token,全站共享 · deepseek-v4-flash-0731 · Input 0 / Output 0 USD credits / 1M
  • openp.ai · test · deepseek-v4-flash-0731 · Input 0.25 / Output 0.5 USD credits / 1M
View all 3 rows →
How this ranking works

All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.

This model has 445 recorded prices; 150 can be compared directly (146 ranked, 4 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 131, price not parsed yet 55, new price under review; showing the previous one 41, billed per request or another unit 25, display unit not confirmed 22, ratio looks unset 21

0 recent · 105 stale (older than 7 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Switch model