Last updated: Aug 16, 2026 49 sources 20 endpoints monitored

DeepSeek

Known for the lowest prices around. The V3 / V4 / R1 lines on the hub, plus DeepSeek's own endpoint.

LLM & Generative AI · comparison · snapshot Aug 16, 2026, 01:47 PM

Cheapest

Lowest floor price per 1M tokens (min of input & output) across every listing.

1
OpenRouter deepseek/deepseek-v4-flash
$0.061
  1. 2
    OpenRouter ~deepseek/deepseek-v4-flash-latest
    $0.064
  2. 3
    OpenRouter deepseek/deepseek-v4-flash-0731
    $0.140
  3. 4
    OpenRouter deepseek/deepseek-chat-v3.1
    $0.250
  4. 5
    OpenRouter deepseek/deepseek-chat
    $0.257
  5. + 11 more listings

Free tier

Listings that cost nothing — price per 1M tokens is $0.

Data incoming

No public snapshot for this ranking yet. Check back after the next daily feed update.

Fastest

Lowest p50 latency in ms. Approximated at the provider endpoint, not per model.

1
OpenRouter
74.8 ms
  1. 2
    DeepSeek
    489.0 ms

Most reliable

Highest share of 200 responses (2xx) from the latest probe snapshot.

1
OpenRouter
1/1 ok
  1. 2
    DeepSeek
    0/1 ok

Overall

Weighted score out of 100 — price 40%, reliability 30%, latency 30% (missing dims skipped & renormalized).

1
OpenRouter
100/100
  1. 2
    DeepSeek price 0 · reliability 0 · latency 0
    0/100

Platform details

per provider
provider model Input /1M Output /1M Latency p50 Status Data time
DeepSeek deepseek-v4-pro $660000 $1980000 489.0 ms err 2026-08-16 13:45:54
OpenRouter deepseek/deepseek-v4-pro $1.17 $2.34 74.8 ms 2xx 100% 2026-08-16 11:08:32

2 rows · snapshot 2026-08-16 13:47:03 · from data/public/prices.json + measurements.json

How to read this page

All rankings are computed from public daily snapshots — verify any result against the source feed below.