InferIndex
Language, English, EN
Account

ModelsDeepSeekDeepSeek V3

DeepSeek V3

deepseek/deepseek-chat128k 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.
$0.463
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.
$0.89
Offers
16
Providers
8

Cheapest right now

NanoGPT

The provider's published policy: prompts are not used for training.

128k

$0.181 blended / 1M tokens

No change7D
in
$0.10
out
$0.425
Cached input
–
Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

DeepSeek V3 costs from $0.181 per million tokens (at a 3:1 input:output mix): the cheapest of 5 comparable offers, at NanoGPT, checked on ; 16 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 (11)

  • $0.45 · Glama via Glama · cannot be designated the cheapest
  • $0.45 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.463 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.463 · DeepInfra via Hugging Face · another route of the same provider
  • $0.463 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.463 · DeepInfra via OpenRouter · another route of the same provider
  • $0.478 · SophNet · cannot be designated the cheapest
  • $0.50 · StreamLake via Kilo Gateway · cannot be designated the cheapest
  • $0.863 · DeepInfra via Requesty · another route of the same provider
  • $0.89 · Novita via Requesty · another route of the same provider
  • $0.90 · Fireworks via LMRouter · cannot be designated the cheapest

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$0.181, NanoGPT–
2026-10-03$0.181, NanoGPT–
2026-10-04$0.181, NanoGPT–
2026-10-05$0.181, NanoGPT–
2026-10-06$0.181, NanoGPT–
2026-10-07$0.181, NanoGPT–
2026-10-08$0.181, NanoGPT–
2026-10-09$0.181, NanoGPT–
2026-10-10$0.181, NanoGPT–
2026-10-11$0.181, NanoGPT–
2026-10-12$0.181, NanoGPT–
2026-10-13$0.181, NanoGPT–
2026-10-14$0.181, NanoGPT–
2026-10-15$0.181, NanoGPT–
2026-10-16$0.181, NanoGPT–
2026-10-17$0.181, NanoGPT–
2026-10-18$0.181, NanoGPT–
2026-10-19$0.181, NanoGPT–
2026-10-20$0.181, NanoGPT–
2026-10-21$0.181, NanoGPT–
2026-10-22$0.181, NanoGPT–
2026-10-23$0.181, NanoGPT–
2026-10-24$0.181, NanoGPT–
2026-10-25$0.181, NanoGPT–
2026-10-26$0.181, NanoGPT–
2026-10-27$0.181, NanoGPT–
2026-10-28$0.181, NanoGPT–
2026-10-29$0.181, NanoGPT–
2026-10-30$0.181, NanoGPT–
2026-10-31$0.181, NanoGPT–

Cheapest offer

Offers

16 of 16 offers

Offers for DeepSeek V3, 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 0.10  0.425 0.181 – 128k
Go to offer at NanoGPT (opens in a new tab)
2 Glama 0.257 1.03  0.45  – 128k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
3 Nous Portal 0.257 1.03  0.45  – 164k 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)
4 StreamLakevia OpenRouter 0.257 1.03  0.45  – 128k Price drop observed: The blended price is 10% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 30, 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)
5 DeepInfra 0.32  0.89  0.463 fp4 164k United States
Go to offer at DeepInfra (opens in a new tab)
6 DeepInfravia Eden AI 0.32  0.89  0.463 fp4 164k 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
7 DeepInfravia Hugging Face 0.32  0.89  0.463 fp4 164k United States
See pricing at Hugging Face (opens in a new tab)
8 DeepInfravia Kilo Gateway 0.32  0.89  0.463 fp4 164k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
9 DeepInfravia OpenRouter 0.32  0.89  0.463 fp4 164k 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)
10 SophNet 0.27  1.10  0.478 – 128k Unverified. No public page for this offer: listed, not designated cheapest
: SophNet (opens in a new tab). No public price page for this model
11 StreamLakevia Kilo Gateway 0.286 1.14  0.50  fp8 128k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
12 Novitavia Requesty 0.40  1.30  0.625 – 128k 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)
13 DeepInfravia Requesty 0.85  0.90  0.863 fp4 128k 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)
14 Novita 0.89  0.89  0.89  – 64k
See pricing at Novita (opens in a new tab)
15 Novitavia Requesty 0.89  0.89  0.89  – 64k Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
See pricing at Requesty (opens in a new tab)
16 Fireworksvia LMRouter 0.90  0.90  0.90  – 128k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LMRouter (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.

4 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. NanoGPT$12.38per month
  2. DeepInfra$32.55per month+$20.17 vs the cheapest
  3. StreamLake$30.87per month+$18.49 vs the cheapest

Host it yourself instead? See the break-even

Compare DeepSeek V3 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-chat
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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