Cost per 1,000 typical chats (600 words in, 150 words out each ≈ 798k input + 200k output tokens). Cheapest 5 per tier.
Budget (output ≤ $1 per 1M tokens)
| Vendor | Model | In $/1M | Out $/1M | Per 1k chats |
|---|
| Meta (Llama) | Llama 3.1 8B Instruct | $0.05 | $0.08 | $0.06 |
| Meta (Llama) | Llama 3.2 1B Instruct | $0.027 | $0.201 | $0.06 |
| Mistral | Ministral 3 3B 2512 | $0.1 | $0.1 | $0.10 |
| Meta (Llama) | Llama 3.2 3B Instruct | $0.05 | $0.33 | $0.11 |
| DeepSeek | DeepSeek V4 Flash 0423 | $0.091 | $0.182 | $0.11 |
Mid-range (output $1–$5 per 1M)
| Vendor | Model | In $/1M | Out $/1M | Per 1k chats |
|---|
| Google | Gemini 3.1 Flash Lite | $0.25 | $1.5 | $0.50 |
| DeepSeek | DeepSeek V4 Flash 0731 | $0.44 | $1.32 | $0.61 |
| Mistral | Mistral Large 3 2512 | $0.5 | $1.5 | $0.70 |
| Mistral | Devstral 2 2512 | $0.4 | $2 | $0.72 |
| Google | Gemini 3.5 Flash Lite | $0.3 | $2.5 | $0.74 |
Premium (output > $5 per 1M)
| Vendor | Model | In $/1M | Out $/1M | Per 1k chats |
|---|
| Mistral | Mistral Medium 3.5 | $1.5 | $7.5 | $2.69 |
| xAI | Grok 4.7 | $2 | $6 | $2.79 |
| xAI | Grok 4.6 | $2 | $6 | $2.79 |
| xAI | Grok 4.5 | $2 | $6 | $2.79 |
| Google | Gemini 3.5 Flash | $1.5 | $9 | $2.99 |
Cheapest model from each vendor
| Vendor | Model | In $/1M | Out $/1M | Per 1k chats |
|---|
| Anthropic | Claude Haiku 5.5 | $0.1 | $0.5 | $0.18 |
| DeepSeek | DeepSeek V4 Flash 0423 | $0.091 | $0.182 | $0.11 |
| Google | Gemini 3.1 Flash Lite | $0.25 | $1.5 | $0.50 |
| Meta (Llama) | Llama 3.1 8B Instruct | $0.05 | $0.08 | $0.06 |
| Mistral | Ministral 3 3B 2512 | $0.1 | $0.1 | $0.10 |
| OpenAI | GPT-6 Luna Pro | $0.1 | $0.5 | $0.18 |
| xAI | Grok Build 0.1 | $1 | $2 | $1.20 |
Prices: list prices from https://openrouter.ai/api/v1/models, fetched 2026-10-26T13:14:57+00:00 (55 models tracked; image, moderation and experimental variants omitted). Standard non-batch, non-cached rates; ~1.33 tokens per word. Estimates only: confirm on each provider's pricing page. Live numbers: tokenbudgeter.com