Mistral: Saba by Mistral AI — $0.200 input / $0.600 output per 1M tokens via OpenRouter. Context: 32K tokens. Pricing last updated Oct 29, 2026.
| Usage | Daily | Monthly |
|---|---|---|
| Chatbot (100/day) | $0.085 | $2.55 |
| Small app (1K/day) | $0.500 | $15.00 |
| Mid-scale (10K/day) | $7.00 | $210.00 |
| Large scale (100K/day) | $160.00 | $4800.00 |
mistralai/mistral-sabaMistral: Saba is an LLM developed by Mistral AI. Input costs $0.200 per million tokens and output costs $0.600 per million tokens via OpenRouter. It supports a context window of 32K tokens.
Via the OpenRouter API:
A token is roughly 0.75 words. For context: a typical user message of 100 words is approximately 133 tokens; a 500-word system prompt is about 650 tokens.
For a typical chatbot application (1,000 requests/day, 1,000 prompt tokens and 500 output tokens per request):
OpenRouter provides a unified API for 200+ LLMs including Mistral: Saba. You can use it with any OpenAI-compatible SDK by setting the base URL to https://openrouter.ai/api/v1 and using your OpenRouter API key. The model ID is mistralai/mistral-saba.
Use the AI Model Cost Comparison tool to compare Mistral: Saba against GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, or any other model side by side. Or use the LLM API Cost Calculator to browse all 456+ models sorted by cost for your specific usage.
mistralai/mistral-saba. OpenRouter provides a unified API compatible with OpenAI's SDK format.