Mercury 2 with Jev
Mercury 2 is a model from Inception, released 2026-03-04. It costs $0.250 per million input tokens and $0.750 per million output tokens, reads up to 128K tokens of context, and writes up to 50,000 tokens in one reply. Through llm11, set model to inception/mercury-2.
- Input price
- $0.250 / 1M
- Output price
- $0.750 / 1M
- Context window
- 128K tokens
- Max output
- 50K tokens
- Cached input
- $0.025 / 1M
- Released
- 2026-03-04
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 68% of the 332 priced models we can call cost more.
Using Mercury 2 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Mercury 2 does the answering when Jev sends it work, or when you name it yourself. At list price Mercury 2 falls in the llm11-fast band, but no pack routes to it because Inception is not one of the labs the packs draw from. You can still pin it: pass inception/mercury-2 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Mercury 2 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00028 | $0.275 |
| Question over retrieved documents | 4,000 / 500 | $0.00137 | $1.38 |
| Long document summary | 30,000 / 1,000 | $0.00825 | $8.25 |
Cheaper models to try
The catalogue has no benchmark score for Mercury 2, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen2.5 72B Instruct | $0.360 | $0.400 | 33K | |
| Qwen Qwen3.6 35B A3B | $0.150 | $1.00 | 262K | |
| Qwen Qwen3 Next 80B A3B Instruct | $0.100 | $1.10 | 262K | |
| DeepSeek DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 1.05M |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="inception/mercury-2",
messages=[{"role": "user", "content": "Hello"}],
)More from Inception
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mercury 2.5 | $0.040 | $0.150 | 260K |
Questions
- What is Mercury 2 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Mercury 2 does the answering when Jev sends it work, or when you name it yourself. At list price Mercury 2 falls in the llm11-fast band, but no pack routes to it because Inception is not one of the labs the packs draw from. You can still pin it: pass inception/mercury-2 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Mercury 2 a System One model?
- No. Mercury 2 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Mercury 2 cost?
- $0.250 per million input tokens and $0.750 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00137, so a thousand of them is about $1.38. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Mercury 2 context window?
- 128,000 tokens, with up to 50,000 tokens in a single reply.
- Does Mercury 2 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Mercury 2 through llm11?
- Yes. Set model to inception/mercury-2 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Mercury 2?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Mercury 2 falls in the llm11-fast band, but no pack routes to it because Inception is not one of the labs the packs draw from. You can still pin it: pass inception/mercury-2 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Mercury 2?
- Nearest in price and below it: Qwen Qwen2.5 72B Instruct at $0.360 in and $0.400 out, Qwen Qwen3.6 35B A3B at $0.150 in and $1.00 out and Qwen Qwen3 Next 80B A3B Instruct at $0.100 in and $1.10 out. The catalogue has no benchmark score for Mercury 2, so this is a price ordering. It does not claim these answer as well.