← All models
Balanced — strong quality at a mid priceOpen Weights
Hy-MT2-30B-A3B Pricing
Tencent · tencent-hy-mt2-30b-a3b
Input / 1M tokens
$0.074
Output / 1M tokens
$0.295
Context window
8,192 tokens
Max output
4,096 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.2068/mo10,000 requests / month$2.07/mo100,000 requests / month$20.68/moEstimate your own workloadOpens the calculator with Hy-MT2-30B-A3B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Low token pricing and open weights support cost-sensitive, self-hosted text workloads. 8k context and 4k output fit standard document and chat use cases.
The business tradeoff
30B scale implies weaker performance on complex reasoning than larger models. Self-hosting introduces latency and infrastructure variability not present in managed APIs.
Cheaper from Tencent
Head-to-head
Vendor list rates, as of Aug 20, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.