NewPoint any agent at UberLLM — one key, every model, list price or less.
UberLLM

Cheapest DeepSeek API (October 2026)

Updated October 31, 2026, 18:00 UTC. UberLLM prices are read live when the page is built (every hour); other providers' prices were checked October 30, 2026 or read from their public price lists at build. UberLLM wrote this page and is one of the providers in it.

On October 31, 2026, the typical DeepSeek model on UberLLM cost 84% less than its list price, with the card fee added (the median over the 9 DeepSeek models we could price both ways, using what buyers paid in the last 24 hours). UberLLM was lowest on both input and output, with the card fee added, for 10 of the 10 DeepSeek models in the table. DeepSeek’s own API charges half price outside its peak hours. UberLLM prices move during the day.

Some UberLLM prices here are more than 70% below list. They are what buyers were billed, not errors. Why so cheap?

ProviderWhat it isHow it prices DeepSeek
UberLLMAPI marketplace, one key for every modelMarket price; lowest in the table on 10 of 10 models
DeepSeekDeepSeek’s own APITwo models; off-peak is half price
DeepInfraRuns open models on its own GPUsIts own per-token price
Novita AIRuns open models on its own GPUsIts own per-token price
Together AIRuns open models on its own GPUsDeepSeek’s own price
FireworksRuns open models on its own GPUsDeepSeek’s price; US-only hosting costs more; batch 50% off
Atlas CloudModel API resellerIts own price, some below DeepSeek’s

UberLLM first because it is lowest on the most models in the table; the rest follow by how they price DeepSeek. An empty cell means we could not confirm it on the provider's own pages.

DeepSeek prices, model by model ($ per 1M input / output tokens)

ModelUberLLMDeepSeekDeepInfraNovita AIOpenRouterTogether AIFireworksAtlas Cloud
DeepSeek V4.1 Flash 1017Why so cheap?$0.00773 / $0.0309$0.30 / $1.20$0.20 / $0.60$0.30 / $1.20$0.15 / $0.60$0.30 / $1.20$0.30 / $1.20$0.30 / $1.20
DeepSeek V4.1 FlashWhy so cheap?$0.00648 / $0.072$0.20 / $0.60$0.30 / $1.20$0.045 / $0.50$0.30 / $1.20$0.30 / $1.20$0.30 / $1.20
DeepSeek V4 ProWhy so cheap?$0.3016 / $0.6032$1.30 / $2.60$1.60 / $3.20$1.60 / $3.20$1.68 / $3.38
DeepSeek V3.2Why so cheap?$0.0026 / $0.0038$0.26 / $0.38$0.26 / $0.38$0.26 / $0.38
DeepSeek V4 Flash$0.0414 / $0.0828$0.09 / $0.18$0.091 / $0.182$0.14 / $0.28
DeepSeek R1$0.2475 / $0.9855$0.70 / $2.40
DeepSeek V3.1Why so cheap?$0.0025 / $0.0095$0.25 / $0.95
DeepSeek V4 Flash 0731Why so cheap?$0.0318 / $0.0635$0.06 / $0.18$0.44 / $1.32$0.119 / $0.238$0.44 / $1.32
DeepSeek V4 Pro 0813Why so cheap?$0.028 / $0.0841$1.32 / $3.96$1.30 / $2.60$1.32 / $3.96$0.115 / $4.00$1.32 / $3.96$1.32 / $3.96
DeepSeek V4 Flash Vision Exp$0.0862 / $0.2587$0.44 / $1.32$0.2156 / $0.6468

UberLLM: the median price buyers paid over the last 24 hours, read October 31, 2026; the 5.5% card fee is not in the cell. DeepInfra, Novita and OpenRouter: each one’s public model list, read when this page was built. DeepSeek (peak price, input on a cache miss), Together, Fireworks and Atlas Cloud: their own pricing pages, checked 2026-10-30. An empty cell: not listed.

Each provider, good and bad

UberLLM

Pick it if: You want the lowest per-token DeepSeek price now, with the same key for GPT, Claude, Gemini and media models.

Watch for: Market prices move during the day and can rise when the lower-priced sellers are busy (cap them with provider.max_price). Requests go to third-party providers, not to DeepSeek itself.

Source: UberLLM DeepSeek prices (live, October 31, 2026)

DeepSeek

Pick it if: You want DeepSeek’s own service and can send work off-peak (peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays).

Watch for: Only the current Flash and V4 Pro models.

Source: DeepSeek pricing (checked 2026-10-30)

DeepInfra

Pick it if: Steady prices on US hosting for open models.

Watch for: Not every DeepSeek version is listed.

Source: its model list (checked 2026-10-30)

Novita AI

Pick it if: Low prices on open models.

Watch for: Check that your DeepSeek version is listed.

Source: its model list (checked 2026-10-30)

Together AI

Pick it if: You also need fine-tuning or dedicated GPUs.

Watch for: No saving against DeepSeek’s price.

Source: Together pricing (checked 2026-10-30)

Fireworks

Pick it if: Fast serving and a batch tier at half price.

Watch for: No V4 Pro listed.

Source: Fireworks pricing (checked 2026-10-30)

Atlas Cloud

Pick it if: The widest list of DeepSeek versions, including V3.2.

Watch for: Prices differ by version; compare per model.

Source: Atlas Cloud pricing (checked 2026-10-30)

How to switch to UberLLM

DeepSeek’s own API, UberLLM and every provider here take OpenAI-style requests: change the base URL, the key and the model id.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",  # was: https://api.deepseek.com
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Get an API keyQuickstart

Questions

When is the DeepSeek API cheapest?

DeepSeek’s own API charges half price off-peak. Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays.

Why are DeepSeek prices on UberLLM so low?

UberLLM is a market: sellers offer DeepSeek capacity, often below DeepSeek’s price, and each request goes to one that can serve it. A request costs what its provider charged, and every request is listed with its cost in Activity.

Can I cap what a DeepSeek request costs on UberLLM?

Yes. Send provider.max_price with the most you will pay per million tokens; the request only goes to sellers at or under it.

Are there other fees on UberLLM?

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.