deepseek-chat API price — 3 gateways compared
Cheapest right now: Requesty at $0.14/MTok in
from $0.14 per
million input tokens · 1.8× spread between gateways
· updated continually
Gateway $ in /MTok $ out /MTok
Context Input price history Model ID Requesty $0.14 $0.28 1,000,000 deepseek/deepseek-chat use OpenRouter fees $0.26 $1.03 163,840 deepseek/deepseek-chat use Glama $0.26 $1.03 128,000 deepseek/deepseek-chat use
Fees beyond the token price OpenRouter : No markup on token prices (provider pass-through), but credit purchases cost 5.5% via card ($0.80 minimum) or 5% via crypto; BYOK usage above the monthly allowance is charged 5%. source Changelog for deepseek-chat
2026-09-27 openrouter raised deepseek-deepseek-chat-output 15.6%: 0.89 → 1.0287 usd_per_mtok 2026-09-27 openrouter cut deepseek-deepseek-chat-input 19.6%: 0.32 → 0.2574 usd_per_mtok 2026-09-17 openrouter cut deepseek-deepseek-chat-output 13.5%: 1.0287 → 0.89 usd_per_mtok 2026-09-17 openrouter raised deepseek-deepseek-chat-input 24.3%: 0.2574 → 0.32 usd_per_mtok 2026-09-10 openrouter raised deepseek-deepseek-chat-output 15.6%: 0.89 → 1.0287 usd_per_mtok 2026-09-10 openrouter cut deepseek-deepseek-chat-input 19.6%: 0.32 → 0.2574 usd_per_mtok 2026-09-03 openrouter cut deepseek-deepseek-chat-output 13.5%: 1.0287 → 0.89 usd_per_mtok 2026-09-03 openrouter raised deepseek-deepseek-chat-input 24.3%: 0.2574 → 0.32 usd_per_mtok 2026-08-27 requesty raised deepseek-chat-output 11.1%: 0.252 → 0.28 usd_per_mtok 2026-08-27 requesty raised deepseek-chat-input 11.1%: 0.126 → 0.14 usd_per_mtok deepseek-chat pricing FAQ
How much does deepseek-chat cost per million tokens? The cheapest tracked gateway charges $0.14 per million input tokens and $0.28 per million output tokens (Requesty). Prices refresh continually.
Which gateway is cheapest for deepseek-chat? Requesty for input tokens and Requesty for output tokens, among the 3 gateways we track.
Do deepseek-chat prices differ between gateways? Yes — the most expensive tracked gateway charges 1.8× the cheapest for input tokens. Identical model, identical tokens, different bill.
← All LLM prices · API
Every datum links its source and is versioned in
public git history .
Data: CC BY 4.0 — cite gpudiff.com. Nameplate specs are vendor claims, not measured
throughput. Vast prices are the 25th percentile of verified marketplace listings
(what a careful buyer actually gets); RunPod prices are list. Outbound provider
links may carry referral codes and sponsored units are labelled; neither ever
affects the numbers. Sponsor this site .