Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. All models overview
  2. Text
  3. Inception

Mercury 2.5 Preview

Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.

  • Reasoning
  • Tool Calling
  • Parallel Tool Calls
  • Structured Output

Added Sep 1, 2026

Pricing

Auto routing · per 1M tokens
Input
$0.04
Output
$0.15
Cache read
$0.0040
Compare provider prices

Specifications

Context window
260K
Max output
65.5K

Benchmarks

No public benchmark scores for this model yet.

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Auto
Auto
Recommended
$0.04$0.15$0.0040N/AN/A

Reliability

Related text models

Compare Mercury 2.5 Preview with similar models from the same provider or model family.

Mercury 3

inception/mercury-3

Mercury 3 is Inception's diffusion language model for fast chat, coding, and multi-step agents. It accepts and generates text, with adjustable reasoning, parallel tool calls, structured JSON output, and a shared 1,000,000-token context window. Responses can use up to 131,072 tokens, including reasoning, within the remaining context.

Mercury 2

mercury-2

Inception Labs' fastest reasoning model with tool calling and structured outputs support.

Mercury Coder Small

mercury-coder-small

Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.

DaisyRose 27B

radixark/daisyrose-27b

DaisyRose 27B is RadixArk’s multimodal reasoning model for coding, tool use and long-horizon agent tasks. Built from Qwen3.8-27B using reinforcement learning without supervised fine-tuning or distillation, it accepts text and images and returns text. It supports function calling, JSON-schema output and a 262,144-token context window, with up to 65,536 output tokens. Thinking is on by default; choose low, medium or high effort, or turn it off. The weights are released under Apache 2.0.

Gemini 4 Neon

google/gemini-4-neon

Google's Gemini 4 Neon is a reasoning model for complex coding, document analysis, scientific problem solving, and multi-step tasks that use tools. It accepts text and images and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output, with up to 983,040 input tokens and 65,536 combined thinking and output tokens per response. Choose low, medium, high, or extra-high thinking; high is the default.

Tencent Hy4 Flash

tencent/hy4-flash

Tencent Hy4 Flash is the smaller, faster and cheaper version of Hy4. It accepts text and images and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. It suits coding, automatic tool calling, structured output and high-volume work. Reasoning is on by default and can be turned off.