Mercury 2
InceptionReleased Mar 4, 2026
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
- Context window
- 128K tokens
- Max output
- 50K tokens
- Input
- text
- Output
- text
- Tokenizer
- Other
- Released
- Mar 4, 2026
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.250 | $0.0075 | $0.258 |
| Output | $0.750 | $0.022 | $0.772 |
| Cache read | $0.025 | $0.0008 | $0.026 |
Benchmarks
Design Arena
| Category | Elo | Win rate | Rank |
|---|---|---|---|
| 3Dmodels | 1054 | 24.8% | #84 |
| Codemodels | 1043 | 22% | #93 |
| Data vizmodels | 993 | 19.1% | #89 |
| Game devmodels | 1044 | 21.4% | #88 |
| UI componentsmodels | 1022 | 20.5% | #85 |
| Websitesmodels | 1039 | 21.7% | #94 |
Head-to-head preference voting. How we filter and rank
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- response_format
- stop
- structured_outputs
- temperature
- tool_choice
- tools
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model inception/mercury-2.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inception/mercury-2",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="inception/mercury-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "inception/mercury-2",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Mercury 2 cost via API?
- Through OpenKey, Mercury 2 costs $0.258 per 1M input tokens and $0.772 per 1M output tokens. That is the provider price ($0.250 / $0.750) plus a flat 3% fee — nothing else.
- What is Mercury 2's context window?
- Mercury 2 accepts up to 128K tokens of context and returns up to 50K tokens per request.
- Is Mercury 2 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "inception/mercury-2" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Mercury 2 support?
- Mercury 2 accepts text input and produces text output.