Skip to main content

Cortecs

Inference host

Cortecs runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.

PricingDocsStatusenterprise@cortecs.aipartner@cortecs.aisupport@cortecs.ai
Visit cortecs.ai
Models103
Cheapest for
3 models
Serves
2 model types
Visits in September 202617K−30.6%Unique visitors 8K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Cortecs

ModelInputOutputvs officialContext
Qwen3 30B-A3B Instruct 2507Cheapest$0.10/1M$0.30/1M——
Qwen3 VL 235B A22B Instruct$0.62/1M$3.13/1M
from $0.88 at Deep Infra
+256%—
Voxtral Small 24B 2507$0.123/1M$0.369/1M
from $0.30 at OpenRouter
+23%—

Cortecs at a glance

103 models in total: 102 text, 1 moderation. The cheapest is Ministral 3B at $0.123 /1M. GPT-6 Astra has the largest context window, 1.05M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is DeepSeek V4 Flash Vision Exp, released Oct 17, 2026.

Cheapest

  1. Ministral 3B$0.123/1M
  2. Mistral Nemo$0.146/1M
  3. Nova Micro 1.0$0.16/1M
  4. Qwen3.5 9B$0.168/1M
  5. GPT OSS 20B$0.168/1M

Largest context

  1. GPT-6 Astra1.05M
  2. GPT-6.1 Sol1.05M
  3. GPT-6 Sol1.05M
  4. GPT-6 Luna1.05M
  5. GPT-5.6 Luna1.05M

Most searched

  1. Gemini 4 Argon2M
  2. Kimi K3658K
  3. GPT-6 Astra580K
  4. Claude Opus 5.5405K
  5. GPT-6.1 Sol384K

Newest

  1. DeepSeek V4 Flash Vision ExpOct 17, 2026
  2. MiniMax-M3.1-FlashOct 17, 2026
  3. Gemini 4 ArgonOct 13, 2026
  4. Claude Haiku 5.5Oct 7, 2026
  5. Mistral Large 4Oct 6, 2026