100,000 Qwen3 Coder Flash (OpenRouter) tokens cost $0.0195 as input or $0.0975 as output. Most workloads land in between — a 70/30 input/output split costs about $0.0429. Verified Aug 26, 2026
Quick answer
For Qwen3 Coder Flash (OpenRouter), 100,000 tokens cost $0.0195 as input or $0.0975 as output. A representative 70/30 workload is about $0.0429.
Method & trust
The page prices the selected token volume using the model's listed input and output rates, then applies a 70/30 input/output split for the representative workload. Cached input, batch discounts, retries, and provider fees can change the final invoice.
Interactive calculator
100,000 in · 0 out
Input price
$0.195 / 1M tokens
Output price
$0.975 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 100,000 tokens buys in practice
$0.0351
80% input / 20% output — short replies over conversation history.
$0.0273
90% input / 10% output — long retrieved context, grounded answers.
$0.0234
95% input / 5% output — full documents in, structured extraction out.
Same 100,000 tokens on other models
Related calculations
FAQ
100,000 input tokens cost $0.0195; 100,000 output tokens cost $0.0975. A typical 70/30 input/output mix costs about $0.0429. Rates: $0.195/M input, $0.975/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 100,000 tokens is roughly 21 requests. For a RAG workload with ~8,500 tokens per request, about 12 requests.
Yes — cached input costs $0.039/M instead of $0.195/M, a 80% discount on repeated context.