Mercury 2.5

inception/mercury-2.5

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

InputText
OutputText
Input / Outputclub$0.0424 / $0.159per 1M tokens · USD
Context window260Ktoken
Maximum output65.5Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.0424/ 1M token
Cache readUS$0.00424/ 1M token
OutputUS$0.159/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
260,000 token
Maximum output
65,536 token
Reasoning
high · medium · low · none

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Mercury 2.5, and who develops it?

Mercury 2.5 is a model from inception. Its model ID on Vecbase is inception/mercury-2.5. Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

How much does Mercury 2.5 cost on Vecbase?

For Mercury 2.5, the Club plan lists USD 0.0424 per 1 million input tokens and USD 0.159 per 1 million output tokens, as of 10/22/2026, 9:25:16 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Mercury 2.5’s context window?

Mercury 2.5 has a context window of 260,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Mercury 2.5?

Mercury 2.5 can generate up to 65,536 tokens per response. Your API or request settings may set a lower limit.

Can Mercury 2.5 call tools in an agent workflow?

Yes. Mercury 2.5 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Mercury 2.5 support structured outputs?

Yes. Mercury 2.5 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Mercury 2.5 support?

Mercury 2.5 accepts Text and produces Text.

Which providers make Mercury 2.5 available through Vecbase?

Vecbase offers Mercury 2.5 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Mercury 2.5?

Use inception/mercury-2.5 as the model identifier for Mercury 2.5. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for Mercury 2.5?

Mercury 2.5 supports these reasoning levels: high, medium, low, and none. Available options depend on your API.

What does an agent need to access Mercury 2.5 through Vecbase?

To use Mercury 2.5, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Mercury 2.5?

We do not yet have a confirmed release date for Mercury 2.5.

Which models can I compare with Mercury 2.5 on Vecbase?

You can compare Mercury 2.5 with Mercury 2 (inception/mercury-2), Vecbase Flash (vecbase-1.0-lite), and Vecbase (vecbase-1.0). Check their capabilities and prices to find the best fit for your task.