Mercury 2.5 pricing and routing profile
Mercury 2.5 from Inception lists at $0.04 per million input tokens and $0.15 per million output tokens, with a 260,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured outputReasoning control
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.0255 |
| Chat reply (2,000 in, 400 out) | $0.14 |
| Retrieval-augmented answer (8,000 in, 500 out) | $0.395 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for Mercury 2.5. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Cheaper models that can answer first
Models priced below Mercury 2.5 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Qwen3.7 Flash | $0.03 / $0.13 | 20% |
| Granite 4.0 Micro | $0.017 / $0.112 | 44% |
| gpt-oss-20b | $0.018 / $0.09 | 49% |
| Ling 3.0 Flash | $0.021 / $0.063 | 52% |
| Ling 3.0 Flash VL | $0.021 / $0.0616 | 52% |
| Mistral Nemo | $0.019 / $0.03 | 64% |
Questions
How much does Mercury 2.5 cost?
Mercury 2.5 lists at $0.04 per million input tokens and $0.15 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.14 per 1,000 requests.
What is the context window of Mercury 2.5?
260,000 tokens.
Can a cheaper model replace Mercury 2.5?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Mercury 2.5 on one half of your requests and make at most three answers worse on the other.