Free Tool
Enter your monthly token usage and instantly compare API costs across 35+ models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more.
| Model | Standard price | Neureus price | Savings |
|---|---|---|---|
| Llama 3.2 1BNeureus-hosted | — | — | Save 10% |
| Llama 3.1 8B InstructMeta | — | — | Save 10% |
| Llama 3.2 3BNeureus-hosted | — | — | Save 10% |
| Qwen 2.5 Coder 32BQwen | — | — | Save 10% |
| Gemini 2.0 FlashGoogle | — | — | Save 10% |
| Mistral Small 3.1Mistral AI | — | — | Save 10% |
| GPT-4o miniOpenAI | — | — | Save 10% |
| Gemini 2.5 FlashGoogle | — | — | Save 10% |
| Command RCohere | — | — | Save 10% |
| DeepSeek V3DeepSeek | — | — | Save 10% |
| Llama 4 Scout 17BNeureus-hosted | — | — | Save 10% |
| Llama 3.3 70BNeureus-hosted | — | — | Save 10% |
| CodestralMistral AI | — | — | Save 10% |
| Llama 3.1 70B InstructMeta | — | — | Save 10% |
| Qwen 2.5 72B InstructQwen | — | — | Save 10% |
| Mistral Small 3.1 24BNeureus-hosted | — | — | Save 10% |
| GPT-4.1 miniOpenAI | — | — | Save 10% |
| DeepSeek R1 32BNeureus-hosted | — | — | Save 10% |
| Nemotron 120BNeureus-hosted | — | — | Save 10% |
| DeepSeek R1DeepSeek | — | — | Save 10% |
| Llama 3.3 70B InstructMeta | — | — | Save 10% |
| QwQ 32BNeureus-hosted | — | — | Save 10% |
| Qwen Coder 32BNeureus-hosted | — | — | Save 10% |
| Claude Haiku 4.5Anthropic | — | — | Save 10% |
| Kimi K2Neureus-hosted | — | — | Save 10% |
| Sonar Large (Online)Perplexity | — | — | Save 10% |
| o4-miniOpenAI | — | — | Save 10% |
| Gemini 2.5 ProGoogle | — | — | Save 10% |
| GPT-4.1OpenAI | — | — | Save 10% |
| Mistral LargeMistral AI | — | — | Save 10% |
| GPT-4oOpenAI | — | — | Save 10% |
| Command R+Cohere | — | — | Save 10% |
| Claude Sonnet 4.6Anthropic | — | — | Save 10% |
| o3OpenAI | — | — | Save 10% |
| Claude Opus 4Anthropic | — | — | Save 10% |
LLM APIs charge per token, not per character or word. One token is roughly 4 characters of English text — a typical 1,000-word document is about 1,300 tokens.
The prompt you send to the model: system instructions, conversation history, context, and the user's message. Input tokens are usually cheaper than output.
The model's response. Output tokens typically cost 3–5× more than input tokens because they're generated one at a time, while input is processed in batch.
Multiply your daily token counts by 30. For a chatbot handling 1,000 conversations/day with average 500 input + 200 output tokens: 15M input + 6M output per month.
Neureus routes every request through a response cache and prompt compression layer, returning savings to you as a permanent 10% discount off OpenRouter published rates.
All 35 models available via one Neureus API key, priced 10% below OpenRouter.
| Model | Context | OpenRouter Input /M | OpenRouter Output /M | Neureus Input /M | Neureus Output /M |
|---|---|---|---|---|---|
| Llama 3.2 1BNeureus-hosted | 128K | $0.027 | $0.20 | $0.024 | $0.18 |
| Llama 3.1 8B InstructMeta | 128K | $0.050 | $0.050 | $0.045 | $0.045 |
| Llama 3.2 3BNeureus-hosted | 128K | $0.051 | $0.34 | $0.046 | $0.30 |
| Qwen 2.5 Coder 32BQwen | 33K | $0.070 | $0.16 | $0.063 | $0.14 |
| Gemini 2.0 FlashGoogle | 1M | $0.10 | $0.40 | $0.090 | $0.36 |
| Mistral Small 3.1Mistral AI | 128K | $0.10 | $0.30 | $0.090 | $0.27 |
| GPT-4o miniOpenAI | 128K | $0.15 | $0.60 | $0.14 | $0.54 |
| Gemini 2.5 FlashGoogle | 1M | $0.15 | $0.60 | $0.14 | $0.54 |
| Command RCohere | 128K | $0.15 | $0.60 | $0.14 | $0.54 |
| DeepSeek V3DeepSeek | 66K | $0.27 | $1.10 | $0.24 | $0.99 |
| Llama 4 Scout 17BNeureus-hosted | 128K | $0.27 | $0.85 | $0.24 | $0.77 |
| Llama 3.3 70BNeureus-hosted | 128K | $0.29 | $2.25 | $0.26 | $2.03 |
| CodestralMistral AI | 256K | $0.30 | $0.90 | $0.27 | $0.81 |
| Llama 3.1 70B InstructMeta | 128K | $0.35 | $0.40 | $0.32 | $0.36 |
| Qwen 2.5 72B InstructQwen | 128K | $0.35 | $0.40 | $0.32 | $0.36 |
| Mistral Small 3.1 24BNeureus-hosted | 128K | $0.35 | $0.56 | $0.32 | $0.50 |
| GPT-4.1 miniOpenAI | 1M | $0.40 | $1.60 | $0.36 | $1.44 |
| DeepSeek R1 32BNeureus-hosted | 32K | $0.50 | $4.88 | $0.45 | $4.39 |
| Nemotron 120BNeureus-hosted | 128K | $0.50 | $1.50 | $0.45 | $1.35 |
| DeepSeek R1DeepSeek | 66K | $0.55 | $2.19 | $0.50 | $1.97 |
| Llama 3.3 70B InstructMeta | 128K | $0.59 | $0.79 | $0.53 | $0.71 |
| QwQ 32BNeureus-hosted | 32K | $0.66 | $1.00 | $0.59 | $0.90 |
| Qwen Coder 32BNeureus-hosted | 32K | $0.66 | $1.00 | $0.59 | $0.90 |
| Claude Haiku 4.5Anthropic | 200K | $0.80 | $4.00 | $0.72 | $3.60 |
| Kimi K2Neureus-hosted | 128K | $0.95 | $4.00 | $0.85 | $3.60 |
| Sonar Large (Online)Perplexity | 127K | $1.00 | $1.00 | $0.90 | $0.90 |
| o4-miniOpenAI | 200K | $1.10 | $4.40 | $0.99 | $3.96 |
| Gemini 2.5 ProGoogle | 1M | $1.25 | $10.00 | $1.13 | $9.00 |
| GPT-4.1OpenAI | 1M | $2.00 | $8.00 | $1.80 | $7.20 |
| Mistral LargeMistral AI | 128K | $2.00 | $6.00 | $1.80 | $5.40 |
| GPT-4oOpenAI | 128K | $2.50 | $10.00 | $2.25 | $9.00 |
| Command R+Cohere | 128K | $2.50 | $10.00 | $2.25 | $9.00 |
| Claude Sonnet 4.6Anthropic | 200K | $3.00 | $15.00 | $2.70 | $13.50 |
| o3OpenAI | 200K | $10.00 | $40.00 | $9.00 | $36.00 |
| Claude Opus 4Anthropic | 200K | $15.00 | $75.00 | $13.50 | $67.50 |
Prices in USD per million tokens. Neureus price = OpenRouter rate × 0.90.
The calculator uses published API pricing from each provider (via OpenRouter's rate card), updated monthly. Actual costs may vary slightly if providers change pricing mid-month.
Input tokens include your system prompt, conversation history, any documents you send, and the user's message. Output tokens are the model's reply. Most LLMs charge more for output than input (usually 3–5× more).
Neureus runs a semantic response cache and prompt compression layer in front of every model. The savings are passed to you as a flat 10% discount.
Yes. Neureus supports BYOK — you supply your provider key, Neureus routes through it, and you keep the direct billing relationship with the provider while still getting Neureus's caching and routing layer.
Free tier includes 500 Neurons/month. No credit card. Access every model in this calculator through one API key — 10% cheaper than going direct.