Mercury 2: API Pricing, Context Window & Benchmarks
Mercury 2 is a language model from Inception, released in February 2026, with a 128K-token context window, and pricing from $0.250/M input and $0.750/M output.
Mercury 2 is the fastest reasoning LLM, built on diffusion-based language model (dLLM) architecture. Instead of generating text token-by-token, it refines multiple text blocks simultaneously, achieving over 1,000 tokens per second on
Mercury 2 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
How Mercury 2 performs across real-world prompt categories.
Performance by conversation depth
How Mercury 2 holds up as conversations get longer.
Quality Tracker
Mercury 2 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Aug 25 2026Mercury 2 pricing
Providers
Mercury 2 starts at $0.250 per million input tokens and $0.750 per million output tokens via Inception.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Inception | $0.250 | — | $0.750 | 128.0K/8.2K | 1.70 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Mercury 2 context window
Input and output token limits for Mercury 2, plus how it ranks on long-context understanding.
Mercury 2 API
Run a request to see the response
Use it in your code
Billed at $0.25 input / $0.75 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="mercury-2",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Mercury 2 latency
Mercury 2 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Mercury 2 examples
Recent arena outputs from Mercury 2, picked from the highest-ranked matchups.
Mercury 2 license
Mercury 2 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Mercury 2 resources
Official sources for Mercury 2: api documentation, official playground, official launch post.
Mercury 2 vs other models
The most-compared alternatives to Mercury 2 are GPT OSS 20B High, Llama 3.1 Nemotron Ultra 253B v1, DeepSeek R1 Zero. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Mercury 2
Models ranked just above and below Mercury 2 by LLM Stats score.
FAQ
Common questions about Mercury 2.