1 million Hy-MT2-30B-A3B (OpenRouter) tokens cost $0.074 as input or $0.295 as output. Most workloads land in between — a 70/30 input/output split costs about $0.1403. Verified Aug 28, 2026
1 million tokens is the rough size of a full codebase, a large corpus, or a significant share of a production day — about 208 chat-style requests (4,000 input + 800 output tokens each). Billed on Hy-MT2-30B-A3B (OpenRouter) at $0.074/M input and $0.295/M output, that volume costs $0.074 as pure input, $0.295 as pure output, or about $0.1403 at a typical 70/30 mix. Hy-MT2-30B-A3B (OpenRouter) has no published cached-input discount, so repeated context bills at the full rate. As a budget-tier model it is priced for high-volume traffic — this is the volume range where it shines.
Interactive calculator
1,000,000 in · 0 out
Input price
$0.074 / 1M tokens
Output price
$0.295 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 1 million tokens buys in practice
$0.1182
80% input / 20% output — short replies over conversation history.
$0.0961
90% input / 10% output — long retrieved context, grounded answers.
$0.085
95% input / 5% output — full documents in, structured extraction out.
Same 1 million tokens on other models
Related calculations
FAQ
1 million input tokens cost $0.074; 1 million output tokens cost $0.295. A typical 70/30 input/output mix costs about $0.1403. Rates: $0.074/M input, $0.295/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 1 million tokens is roughly 208 requests. For a RAG workload with ~8,500 tokens per request, about 118 requests.
Hy-MT2-30B-A3B (OpenRouter) has no published cached-input discount on its official pricing page; all input is billed at $0.074/M.