Cortecs
Inference hostCortecs runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Models103
- Cheapest for
- 3 models
- Serves
- 2 model types
Visits in September 202617K−30.6%Unique visitors 8K
- Apr
- May
- Jun
- Jul
- Aug
- Sep
Models by type
Models on Cortecs
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
 Ministral 3BMistral | $0.123/1M | $0.123/1M from $0.10 at DevPass (LLM Gateway) | +23% | — |
 MiniMax M2.1MiniMax | $0.36/1M | $1.44/1M from $0.864 at APIMart | +67% | — |
| Mistral Small 4Mistral | $0.157/1M | $0.628/1M from $0.60 at EmpirioLabs AI | +5% | — |
 Nemotron 3 Nano 30B A3BNVIDIA | $0.06/1M | $0.241/1M from $0.20 at Novita AI | +20% | — |
| Ministral 8BMistral | $0.18/1M | $0.18/1M from $0.143 at AI/ML API | +26% | — |
 MiniCPM V 4.5OpenBMBOnly here | $0.654/1M | $1.10/1M | — | — |
 Apertus 70BSwiss AiCheapest | $1.40/1M | $2.24/1M | — | — |
| Claude Haiku 4.5 (latest)Anthropic | $1/1M | $5.01/1M from $4 at APIMart | ±0% | — |
| Claude Opus 4.5 (latest)Anthropic | $5.34/1M | $26.69/1M from $20 at APIMart | +7% | — |
| Claude Opus 4.6Anthropic | $5.34/1M | $26.69/1M from $20 at APIMart | +7% | — |
| Claude Opus 4.7Anthropic | $5.46/1M | $27.32/1M from $20 at APIMart | +9% | — |
| Claude Opus 4.8Anthropic | $5.46/1M | $27.32/1M from $20 at APIMart | +9% | — |
| Claude Sonnet 4.5 (latest)Anthropic | $3/1M | $15.02/1M from $12 at APIMart | ±0% | — |
| Codestral 25.08Mistral | $0.369/1M | $1.11/1M from $0.90 at DevPass (LLM Gateway) | +23% | — |
 Deepseek 3.2DeepSeek | $0.503/1M | $1.51/1M from $0.308 at APIMart | +389% | — |
| DeepSeek V4 ProDeepSeek | $2.01/1M | $4.02/1M from $1.58 at CometAPI | +103% | — |
| Devstral-2-123B-Instruct-2512-int4-AutoRoundMistral | $0.48/1M | $2.40/1M from $2 at Amazon Bedrock | +20% | — |
 Gemini 3.1 Flash LiteGoogle | $0.273/1M | $1.64/1M from $1.20 at CometAPI | +9% | — |
| Gemini 3.5 FlashGoogle | $1.66/1M | $9.95/1M from $2.70 at Kie.ai | +268% | — |
| Gemini 3.5 Flash LiteGoogle | $0.331/1M | $2.76/1M from $2 at APIMart | +11% | — |
| Gemini 3.6 FlashGoogle | $0.753/1M | $3.77/1M from $3 at CometAPI | ±0% | — |
| Gemini 3.7 FlashGoogle | $0.753/1M | $3.77/1M from $1.13 at Kie.ai | +235% | — |
| GPT OSS Safeguard 120BOpenAI | $0.18/1M | $0.701/1M from $0.60 at Amazon Bedrock | +17% | — |
| GPT-4.1 miniOpenAI | $0.437/1M | $1.71/1M from $1.28 at APIMart | +7% | — |
| GPT-4.1 nanoOpenAI | $0.112/1M | $0.437/1M from $0.32 at APIMart | +9% | — |
| GPT-5.1OpenAI | $1.38/1M | $11.01/1M from $8 at APIMart | +10% | — |
| GPT-5.6 TerraOpenAI | $2.21/1M | $13.26/1M from $9.60 at APIMart | +11% | — |
| Hermes 4 405BNous Research | $1/1M | $3/1M from $3 at OpenRouter | ±0% | — |
| Kolibri 1Aleph AlphaOnly here | $0.168/1M | $0.616/1M | — | — |
| MiniMax M2MiniMax | $0.35/1M | $1.41/1M from $1 at DevPass (LLM Gateway) | +41% | — |
| Ministral 14BMistral | $0.241/1M | $0.241/1M from $0.20 at DevPass (LLM Gateway) | +20% | — |
| Mistral 7B Instruct V0.2MistralCheapest | $0.16/1M | $0.221/1M | — | — |
| Mistral Large 2402MistralOnly here | $4.30/1M | $13.01/1M | — | — |
| Mistral Large 3Mistral | $0.616/1M | $1.85/1M from $1.50 at AIHubMix | +23% | — |
| Mistral Small 3.1 24BMistral | $0.112/1M | $0.336/1M from $0.33 at Requesty | +2% | — |
| Mistral Small 3.2 24BMistral | $0.101/1M | $0.313/1M from $0.20 at Deep Infra | +57% | — |
| Mixtral 8x7B Instruct v0.1 (Deep Infra)MistralOnly here | $0.49/1M | $0.761/1M | — | — |
| Nemotron-nano 12b v2-vlNVIDIA | $0.241/1M | $0.711/1M from $0.60 at Vercel AI Gateway | +18% | — |
 Nova 2 Lite (EU)Amazon | $0.375/1M | $3.16/1M from $2.50 at Amazon Bedrock | +26% | — |
| Nova Lite 1.0Amazon | $0.069/1M | $0.276/1M from $0.24 at OpenRouter | +15% | — |
| Nova Micro 1.0Amazon | $0.04/1M | $0.16/1M from $0.14 at OpenRouter | +14% | — |
| Nova Pro 1.0Amazon | $0.922/1M | $3.69/1M from $3.20 at OpenRouter | +15% | — |
| OpenAI GPT-4.1OpenAI | $2.20/1M | $8.81/1M from $6.40 at APIMart | +10% | — |
| OpenAI GPT-4o miniOpenAI | $0.16/1M | $0.641/1M from $0.48 at APIMart | +7% | — |
| OpenAI GPT-5 MiniOpenAI | $0.28/1M | $2.20/1M from $1.60 at APIMart | +10% | — |
| OpenAI GPT-5 NanoOpenAI | $0.06/1M | $0.441/1M from $0.32 at APIMart | +10% | — |
| OpenAI GPT-5.4OpenAI | $2.91/1M | $15.53/1M from $12 at APIMart | +4% | — |
| Pixtral Large (25.02) (US)Mistral | $2/1M | $6.01/1M from $6 at Amazon Bedrock | ±0% | — |
 Qwen2.5-VL 72B InstructAlibaba | $1.02/1M | $1.02/1M from $0.50 at AIHubMix | +104% | — |
| Qwen3 235B A22B Instruct 2507Alibaba | $0.20/1M | $0.601/1M from $0.10 at Requesty | +501% | — |
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
- Ministral 3B$0.123/1M
- Mistral Nemo$0.146/1M
- Nova Micro 1.0$0.16/1M
- Qwen3.5 9B$0.168/1M
- GPT OSS 20B$0.168/1M
Largest context
- GPT-6 Astra1.05M
- GPT-6.1 Sol1.05M
- GPT-6 Sol1.05M
- GPT-6 Luna1.05M
- GPT-5.6 Luna1.05M
Most searched
- Gemini 4 Argon2M
- Kimi K3658K
- GPT-6 Astra580K
- Claude Opus 5.5405K
- GPT-6.1 Sol384K
Newest
- DeepSeek V4 Flash Vision ExpOct 17, 2026
- MiniMax-M3.1-FlashOct 17, 2026
- Gemini 4 ArgonOct 13, 2026
- Claude Haiku 5.5Oct 7, 2026
- Mistral Large 4Oct 6, 2026