AI Model Catalog
Browse 35 models from 10 providers — all accessible through one API. Neureus prices every model at 10% below published OpenRouter rates.
This directory highlights Neureus's core catalog. The full, always-current model list (62 models as of this writing) is available live at GET /ai/models and in the app dashboard.
| Model | Context | Input /M | Output /M | Neureus In | Neureus Out | Capabilities |
|---|---|---|---|---|---|---|
| GPT-4.1OpenAI | 1M | $2.00 | $8.00 | $1.80 | $7.20 | ChatVisionCode+3 |
| GPT-4.1 miniOpenAI | 1M | $0.40 | $1.60 | $0.36 | $1.44 | ChatVisionCode+2 |
| GPT-4oOpenAI | 128K | $2.50 | $10.00 | $2.25 | $9.00 | ChatVisionCode+3 |
| GPT-4o miniOpenAI | 128K | $0.15 | $0.60 | $0.14 | $0.54 | ChatVisionCode+2 |
| o3OpenAI | 200K | $10.00 | $40.00 | $9.00 | $36.00 | Advanced reasoningCodeMath+2 |
| o4-miniOpenAI | 200K | $1.10 | $4.40 | $0.99 | $3.96 | ReasoningCodeMath+2 |
| Claude Opus 4Anthropic | 200K | $15.00 | $75.00 | $13.50 | $67.50 | ChatVisionCode+3 |
| Claude Sonnet 4.6Anthropic | 200K | $3.00 | $15.00 | $2.70 | $13.50 | ChatVisionCode+3 |
| Claude Haiku 4.5Anthropic | 200K | $0.80 | $4.00 | $0.72 | $3.60 | ChatVisionCode+2 |
| Gemini 2.5 ProGoogle | 1M | $1.25 | $10.00 | $1.13 | $9.00 | ChatVisionCode+3 |
| Gemini 2.5 FlashGoogle | 1M | $0.15 | $0.60 | $0.14 | $0.54 | ChatVisionCode+2 |
| Gemini 2.0 FlashGoogle | 1M | $0.10 | $0.40 | $0.090 | $0.36 | ChatVisionCode+2 |
| Llama 3.3 70B InstructMeta | 128K | $0.59 | $0.79 | $0.53 | $0.71 | ChatCodeFunction calling+1 |
| Llama 3.1 70B InstructMeta | 128K | $0.35 | $0.40 | $0.32 | $0.36 | ChatCodeFunction calling |
| Llama 3.1 8B InstructMeta | 128K | $0.050 | $0.050 | $0.045 | $0.045 | ChatCodeEdge inference+1 |
| Mistral LargeMistral AI | 128K | $2.00 | $6.00 | $1.80 | $5.40 | ChatCodeMultilingual+2 |
| Mistral Small 3.1Mistral AI | 128K | $0.10 | $0.30 | $0.090 | $0.27 | ChatVisionCode+2 |
| CodestralMistral AI | 256K | $0.30 | $0.90 | $0.27 | $0.81 | Code generationCode completionCode review+2 |
| DeepSeek R1DeepSeek | 66K | $0.55 | $2.19 | $0.50 | $1.97 | Advanced reasoningMathCode+2 |
| DeepSeek V3DeepSeek | 66K | $0.27 | $1.10 | $0.24 | $0.99 | ChatCodeMath+1 |
| Command R+Cohere | 128K | $2.50 | $10.00 | $2.25 | $9.00 | ChatRAGTool use+2 |
| Command RCohere | 128K | $0.15 | $0.60 | $0.14 | $0.54 | ChatRAGTool use+1 |
| Qwen 2.5 72B InstructQwen | 128K | $0.35 | $0.40 | $0.32 | $0.36 | ChatCodeMultilingual+1 |
| Qwen 2.5 Coder 32BQwen | 33K | $0.070 | $0.16 | $0.063 | $0.14 | Code generationCode completionDebugging+1 |
| Sonar Large (Online)Perplexity | 127K | $1.00 | $1.00 | $0.90 | $0.90 | ChatWeb searchCitations+1 |
| Llama 3.3 70BNeureus-hosted | 128K | $0.29 | $2.25 | $0.26 | $2.03 | ChatReasoningCode+1 |
| Llama 4 Scout 17BNeureus-hosted | 128K | $0.27 | $0.85 | $0.24 | $0.77 | ChatVisionCode |
| DeepSeek R1 32BNeureus-hosted | 32K | $0.50 | $4.88 | $0.45 | $4.39 | ChatReasoningMath+1 |
| QwQ 32BNeureus-hosted | 32K | $0.66 | $1.00 | $0.59 | $0.90 | ChatReasoningMath |
| Qwen Coder 32BNeureus-hosted | 32K | $0.66 | $1.00 | $0.59 | $0.90 | ChatCodeDebugging |
| Kimi K2Neureus-hosted | 128K | $0.95 | $4.00 | $0.85 | $3.60 | ChatReasoningLong context+1 |
| Mistral Small 3.1 24BNeureus-hosted | 128K | $0.35 | $0.56 | $0.32 | $0.50 | ChatVisionCode+1 |
| Nemotron 120BNeureus-hosted | 128K | $0.50 | $1.50 | $0.45 | $1.35 | ChatReasoningCode |
| Llama 3.2 3BNeureus-hosted | 128K | $0.051 | $0.34 | $0.046 | $0.30 | ChatFast |
| Llama 3.2 1BNeureus-hosted | 128K | $0.027 | $0.20 | $0.024 | $0.18 | ChatFast |
No models match your filters.
Neureus routes your request to the right model, caches responses at the edge, and tracks every token — per tenant, with spend caps and PII guards built in.