How much does Mercury cost?

Mercury costs $0.2500 per 1M input tokens and $0.7500 per 1M output tokens on BazaarLink. No markup over provider pricing.

What is Mercury's context window?

Mercury supports a 128K token (128,000) context window.

Does Mercury support tool calling / function calling?

Tool calling support for Mercury depends on the provider's current capabilities. See /docs/api for the definitive supported-parameters list per model.

Can I send images to Mercury?

Mercury is a text-only model. For image input, use a multimodal model like a vision-capable variant.

Is Mercury free on BazaarLink?

Mercury is a paid model. BazaarLink offers a free tier on other models — see /free for the current free-tier model list.

Who provides Mercury?

Mercury is provided by inception. BazaarLink routes requests to inception's production inference infrastructure without modification to the request or response format.

How does Mercury compare to other models?

See /models for a side-by-side table of all major models BazaarLink supports, filterable by price, context length, and capabilities.

Can I use Mercury with LangChain or Vercel AI SDK?

Yes. Both LangChain (via ChatOpenAI with base_url) and Vercel AI SDK (via @ai-sdk/openai with baseURL) work out of the box — just use "mercury" as the model identifier.

Mercury

Name: Mercury API
Brand: inception

Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the [blog post] (https://www.inceptionlabs.ai/blog/introducing-mercury) here.

Intelligence#170 / 563

Artificial Analysis Intelligence Index

Speed#1 / 576

1036.6

Output tokens per second (median)

Input Price#305 / 576

$0.25NT$ 8

USD / 1M tokens

Output Price#301 / 576

$0.75NT$ 24

USD / 1M tokens

First-token latency#504 / 576

3.39s

Time to first token (AA median)

Provider	inception
Released	2025年6月
Model ID	`mercury`

Technical specifications

Context window

128K tokens

Reasoning

—

Input

Text

Output

Text

此模型已下架 — API 呼叫會回傳 HTTP 410，但本頁面保留以利歷史查詢（評測資料維持顯示）。

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$0.25NT$ 8

Output$0.75NT$ 24

Cache read—

Cache write—

3:1 blended (est.)$0.38NT$ 12

All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$0.25

Output$0.75

Cache readAA not tracked

Cache writeAA not tracked

3:1 blended$0.38

✓ Matches market reference — BazaarLink does not mark up.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 25

Coding

Math

MMLU

GPQA 77

This modelCategory leader

Overall intelligence

#170out of 563 models

Aggregated across academic benchmarks

Time to first token

#504out of 576 models

AA 全球 p50：3.39 秒

Intelligence

Mid-tier

This model

Category leader

Median

GPQA

77%

—

This model

77%

Category leader

94%

Median

68%

HLE

16%

—

This model

16%

Category leader

53%

Median

SciCode

39%

—

This model

39%

Category leader

60%

Median

33%

IFBench

70%

—

This model

70%

Category leader

83%

Median

44%

τ²-Bench Telecom

71%

—

This model

71%

Category leader

99%

Median

46%

AA-LCR

36%

—

This model

36%

Category leader

76%

Median

39%

Terminal-Bench Hard

27%

—

This model

27%

Category leader

66%

Median

14%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30

2GPT-5.6 Sol (max)openai/gpt-5-6-sol77$5 / $30

3GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30

4GPT-5.6 Terra (max)openai/gpt-5-6-terra77$2.5 / $15

5Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)anthropic/claude-fable-577$10 / $50

AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use Mercury via BazaarLink API — just change the base_url:

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://bazaarlink.ai/api/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="mercury",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bazaarlink.ai/api/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "mercury",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use Mercury via BazaarLink?

✓USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
✓OpenAI-compatible API — zero code changes required
✓Automatic failover — multi-provider redundancy for the same model
✓Chinese-language support — local team, instant help

Try Now ← All Models

Frequently Asked Questions

What is Mercury?

How much does the Mercury API cost?

Mercury costs $0.2500 per 1K input tokens and $0.7500 per 1K output tokens when accessed through BazaarLink.

How do I use Mercury with the OpenAI SDK?

Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "mercury". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for Mercury?

Mercury supports a context window of 128,000 tokens.

Is Mercury available for free?

Mercury is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

中轉站誠信檢測 · BazaarLink 獨家

尚無此模型的檢測資料

BazaarLink Probe 對聲稱提供此模型的 endpoint 進行家族指紋驗證與 V3 子模型對照。如發現行為與真貨基準不符，會列入異常案例。

查看完整檢測報告 →

Related Models & Links

All Models API Documentation API Latency Probe