deepseek-chat-v3.1 API price — 2 gateways compared
Cheapest right now: Glama at $0.25/MTok in
from $0.25 per
million input tokens · same price on every gateway
· updated continually
Gateway $ in /MTok $ out /MTok
Context Input price history Model ID OpenRouter fees $0.25 $0.95 163,840 deepseek/deepseek-chat-v3.1 use Glama $0.25 $0.95 163,840 deepseek/deepseek-chat-v3.1 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-v3.1
2026-09-09 openrouter listed deepseek-deepseek-chat-v3.1-output at 0.95 usd_per_mtok2026-09-09 openrouter listed deepseek-deepseek-chat-v3.1-input at 0.25 usd_per_mtok2026-09-08 openrouter delisted deepseek-deepseek-chat-v3.1-output2026-09-08 openrouter delisted deepseek-deepseek-chat-v3.1-input2026-09-03 openrouter listed deepseek-deepseek-chat-v3.1-output at 1.65 usd_per_mtok2026-09-03 openrouter listed deepseek-deepseek-chat-v3.1-input at 0.55 usd_per_mtok2026-09-02 openrouter delisted deepseek-deepseek-chat-v3.1-output2026-09-02 openrouter delisted deepseek-deepseek-chat-v3.1-input2026-08-23 openrouter listed deepseek-deepseek-chat-v3.1-output at 1.65 usd_per_mtok2026-08-23 openrouter listed deepseek-deepseek-chat-v3.1-input at 0.55 usd_per_mtok2026-08-22 openrouter delisted deepseek-deepseek-chat-v3.1-output2026-08-22 openrouter delisted deepseek-deepseek-chat-v3.1-inputdeepseek-chat-v3.1 pricing FAQ
How much does deepseek-chat-v3.1 cost per million tokens? The cheapest tracked gateway charges $0.25 per million input tokens and $0.95 per million output tokens (Glama). Prices refresh continually.
Which gateway is cheapest for deepseek-chat-v3.1? Glama for input tokens and Glama for output tokens, among the 2 gateways we track.
Do deepseek-chat-v3.1 prices differ between gateways? No — every tracked gateway currently charges the same per-token price, so the difference between them is fees and routing, not token cost.
← 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 .