Inception: Mercury Coder✓ Catalog verified
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 and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the blog post here.
Overview
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 and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the blog post here.
Access: available through the official Inception API. Context window: 128K.
Specifications
| API identifier | inception/mercury-coder |
| Provider | Inception |
| Model type | Text LLM |
| Context window | 128K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Apr 30, 2025 |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_p": null,
"temperature": 0,
"frequency_penalty": null
}Pricing
Live pricing components for inception/mercury-coder as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $2.5e-7 | $0.25 / 1M | Per input token |
| Completion tokens | $7.5e-7 | $0.75 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.28Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call Inception: Mercury Coder through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="inception/mercury-coder",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| AllenAI: Olmo 2 32B Instruct | Allenai | 128K | $0.05 | View → |
| Amazon: Nova Micro 1.0 | Amazon | 128K | $0.04 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does Inception: Mercury Coder cost?
$0.25 per 1M input tokens and $0.75 per 1M output tokens on the official Inception API.
What is the context window of Inception: Mercury Coder?
Inception: Mercury Coder supports up to 128K tokens of context.
Does Inception: Mercury Coder support tool / function calling?
Yes, Inception: Mercury Coder supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access Inception: Mercury Coder?
Use the official Inception API with the model id `inception/mercury-coder`. See the Quick start section above for code examples.