Mercury 2.5
$0.04 per 1M input tokens and $0.15 per 1M output tokens · 260K context · tools, reasoning, JSON.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Mercury 2.5 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $19.22 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $4.40 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $8.28 |
| Content generation 30 long articles a day | $0.446 |
| Classification / extraction 100,000 short items a day | $42.75 |
Price history
We started tracking Mercury 2.5 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Cheaper alternatives to Mercury 2.5
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Ling 3.0 Flash inclusionAI | $0.021 | $0.063 | 262K | toolsreasoningJSONopen weights |
| gpt-oss-20b OpenAI | $0.018 | $0.09 | 131K | toolsreasoningJSONopen weights |
| Mistral Nemo Mistral AI | $0.029 | $0.03 | 131K | toolsJSONopen weights |
How to pay less for Mercury 2.5
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $27.00 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Ling 3.0 Flash (similar capabilities) | $9.22 | $17.78 (66%) |
| Use prompt caching (60% of input cached) | $19.22 | $7.78 (29%) |
Other workloads: cut-your-bill tool for Mercury 2.5.
Specifications
| Model ID | inception/mercury-2.5 |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | No |
| Released | Sep 8, 2026 |
FAQ
- How much does Mercury 2.5 cost?
- $0.04 per million input tokens and $0.15 per million output tokens; cached input costs $0.0040 per million. Prices as of Oct 21, 2026.
- What is the context window of Mercury 2.5?
- 260K tokens, with up to 66K output tokens per response.
- Does Mercury 2.5 support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Mercury 2.5?
- Models with the same key capabilities for at least 20% less include Ling 3.0 Flash ($0.021 / $0.063), gpt-oss-20b ($0.018 / $0.09), Mistral Nemo ($0.029 / $0.03).
More from Inception: all Inception models · how we collect prices