LIVE
BODYBUILDER$-1000000.00 5.4%
GLM-4-LONG$0.00 14.1%
GEMINI-2.0-FLA$0.30 20.0%
GEMINI-2.0-FLA$0.40 6.6%
-CF$0.00 9.7%
DEEPSEEK-V4-FL$0.28 26.3%
LLAMA-4-MAVERI$0.60 11.9%
GROK-4-FAST$0.50 6.0%
QWEN-PLUS$0.78 0.6%
MINIMAX-M2.1$0.95 2.6%
MINIMAX-M2$1.00 2.9%
MINIMAX-01$1.10 8.0%
GPT-4.1-MINI$1.60 13.7%
GROK-4-1-FAST-$0.50 8.9%
GPT-4.1-MINI-2$1.60 31.8%
XAI$0.00 4.5%
MINIMAX-M2.7$0.00 9.9%
QWEN3.5-FLASH-$0.26 31.0%
GPT-4.1-NANO$0.40 13.0%
GEMINI-2.5-FLA$0.40 0.8%
DEEPSEEK-AI$0.00 27.0%
GROK-4.1-FAST$0.50 16.4%
MINIMAX-M3$1.20 6.1%
GOOGLE$1.50 3.4%
AUTO$0.00 9.7%
GOOGLE$0.00 27.8%
MINIMAX-M2.7$1.20 7.2%
GOOGLE$0.00 0.6%
BODYBUILDER$-1000000.00 5.4%
GLM-4-LONG$0.00 14.1%
GEMINI-2.0-FLA$0.30 20.0%
GEMINI-2.0-FLA$0.40 6.6%
-CF$0.00 9.7%
DEEPSEEK-V4-FL$0.28 26.3%
LLAMA-4-MAVERI$0.60 11.9%
GROK-4-FAST$0.50 6.0%
QWEN-PLUS$0.78 0.6%
MINIMAX-M2.1$0.95 2.6%
MINIMAX-M2$1.00 2.9%
MINIMAX-01$1.10 8.0%
GPT-4.1-MINI$1.60 13.7%
GROK-4-1-FAST-$0.50 8.9%
GPT-4.1-MINI-2$1.60 31.8%
XAI$0.00 4.5%
MINIMAX-M2.7$0.00 9.9%
QWEN3.5-FLASH-$0.26 31.0%
GPT-4.1-NANO$0.40 13.0%
GEMINI-2.5-FLA$0.40 0.8%
DEEPSEEK-AI$0.00 27.0%
GROK-4.1-FAST$0.50 16.4%
MINIMAX-M3$1.20 6.1%
GOOGLE$1.50 3.4%
AUTO$0.00 9.7%
GOOGLE$0.00 27.8%
MINIMAX-M2.7$1.20 7.2%
GOOGLE$0.00 0.6%
USCodeMERCURY-CODER Live · updated daily

mercury-coder

Inception
Efficiency score
89/100
+1.5%
Input price
$0.25/ 1M tokens
Output price
$0.75/ 1M tokens
Context window
128K
Throughput
142tok/s
Availability
99.1%
Cost / task
$0.001

Capabilities

Accepts (input)
Text
Produces (output)
Text

7-day heat trend

+1.5%

Pricing breakdown

Input price
$0.25/ 1M tokens
$0.0003 / 1K
Output price
$0.75/ 1M tokens
$0.0008 / 1K
Blended price
$0.63/ 1M tokens
$0.0006 / 1K

Typical 3:1 output-to-input mix, per 1M tokens

Estimated monthly cost by workload

Chat assistant
$165.00/ mo
1K in · 400 out · 10K req/day
RAG / long context
$367.50/ mo
8K in · 600 out · 5K req/day
Agent / tool use
$450.00/ mo
3K in · 1.5K out · 8K req/day
Estimate your cost

Market position

  • Cheaper than 26% of tracked models
  • Faster than 39% of tracked models
  • Efficiency rank: #343 of 1105

Best suited for

Code generation, refactoring and review, and developer-tooling workloads with large context.

About mercury-coder

Mercury Coder 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 Claude 3.5 Haiku...

mercury-coder is a Code model from Inception (US). HotON.ai tracks it at $0.25 per 1M input tokens and $0.75 per 1M output tokens, with a 128K-token context window, ~142 tokens/sec throughput and 99.1% availability. Its composite efficiency score is 89/100 at an estimated $0.001 per successful task.

Frequently asked questions

How much does mercury-coder cost per 1M tokens?+

mercury-coder is tracked at $0.25 per 1M input tokens and $0.75 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.63 per 1M tokens. Figures are illustrative demo data.

What is mercury-coder best for?+

Code generation, refactoring and review, and developer-tooling workloads with large context.

How fast is mercury-coder?+

mercury-coder delivers about 142 tokens/sec with 99.1% tracked availability, suitable for latency-sensitive, real-time applications.

Is mercury-coder cheaper than other AI models?+

Within the HotON.ai tracked set, mercury-coder is cheaper than 26% of models on input price and ranks #343 of 1105 by overall efficiency.

Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.