🔔 Watch Models for Price Drops & Embed Live SVG Badges
Get instant alerts when OpenAI, Anthropic, Google, or DeepSeek cut token prices, or embed a live auto-updating SVG price badge in your GitHub README.
GitHub README Markdown Badge:
Smart Router Configuration & Cost Failover: Mistral Large 4 "Le Chonk" (mistralai/mistral-large-4-0) to DeepSeek V4 Pro 0813 (deepseek/deepseek-v4-pro-0813)
Production LLM API routing configuration, TTFT latency SLA (<400ms), and contribution margin failover benchmark generated by TokenMargin.dev.
1. Pricing & Latency Benchmark Summary
Primary Model (Mistral Large 4 "Le Chonk" — mistralai/mistral-large-4-0): $0.70 / 1M input tokens, $2.10 / 1M output tokens | TTFT: 175ms | Throughput: 135 tok/s