50% off Mercury 3
50% off Mercury Decide
Models
| Model | Input Price (1M Tokens) | Cached Input Price (1M Tokens) | Output Price (1M Tokens) | Supported Endpoints | Context Window | Max Output Tokens | Features | Supported Formats |
|---|---|---|---|---|---|---|---|---|
| Mercury 3 | v1/chat/completions | Chat: 1M | 131,072 | Tool CallingStructured Outputs | Text | |||
| Mercury Voice | v1/chat/completions | Chat: 128K | 50,000 | Tool CallingStructured Outputs | Text | |||
| Mercury Decide | $0 | $0 | v1/decisions | — | — | ClassificationScoringExtraction | Text / JSON / Image | |
| Mercury 2.5 | $0.20 | $0.02 | $0.75 | v1/chat/completions | Chat: 260K | 65,536 | Tool CallingStructured Outputs | Text |
| Mercury 2 | $0.25 | $0.025 | $0.75 | v1/chat/completions | Chat: 128K | 50,000 | Tool CallingStructured Outputs | Text |
| Mercury Edit 2 | $0.25 | $0.025 | $0.75 | v1/fim/completionsv1/edit/completions | FIM: 32K NextEdit: 32K | 8,192 | Text |
- Mercury 3
- Mercury Voice
- Mercury Decide
- Mercury 2.5
- Mercury 2
- Mercury Edit 2
Our most intelligent model yet, with a 1M-token context window, up to 131,072 output tokens, and
instant, low, medium, and high reasoning effort. Temperature is adjustable from 0.5 to 1.0.Mercury 3 is 50% off at launch: $0.10 per million input tokens and $0.35 per million output tokens (regularly $0.20 and $0.70).Export your API key as an environment variable in your terminal.export INCEPTION_API_KEY="your_api_key_here"
set INCEPTION_API_KEY=your_api_key_here
$env:INCEPTION_API_KEY="your_api_key_here"
Example Usage
Chat Completions
v1/chat/completionscurl https://api.inceptionlabs.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $INCEPTION_API_KEY" \
-d '{
"model": "mercury-3",
"messages": [
{"role": "user", "content": "What is a diffusion model?"}
],
"reasoning_effort": "medium",
"max_completion_tokens": 8192
}'
from inceptionai import Inception
client = Inception() # reads INCEPTION_API_KEY from the environment
completion = client.chat.completions.create(
model="mercury-3",
messages=[{"role": "user", "content": "What is a diffusion model?"}],
reasoning_effort="medium",
max_completion_tokens=8192,
)
print(completion.choices[0].message.content)
import Inception from 'inceptionai';
const client = new Inception(); // reads INCEPTION_API_KEY from the environment
const completion = await client.chat.completions.create({
model: 'mercury-3',
messages: [{ role: 'user', content: 'What is a diffusion model?' }],
reasoning_effort: 'medium',
max_completion_tokens: 8192,
});
console.log(completion.choices[0]?.message.content);
A diffusion LLM tuned for voice agents. It reasons, calls tools, returns structured outputs, and follows long system prompts while keeping latency low enough for natural conversation.Mercury Voice is available to enterprise customers through the OpenAI-compatible Inception API, and works with LiveKit, Pipecat, Vapi, Retell, or your own voice stack. It supports
low, medium, and high reasoning effort. Temperature is adjustable from 0.5 to 1.0.Mercury 3 is 50% off at launch: $0.10 per million input tokens and $0.35 per million output tokens (regularly $0.20 and $0.70).Get access to Mercury Voice
Contact [email protected] to enable Mercury Voice for your organization.
Evaluate named questions against shared context with
mercury-decide at v1/decisions. Get binary probabilities, categorical choices, or ordinal scores with typed answers, or extract exact spans of the input text.Only input tokens are billed, at $0.02 per million tokens (50% off the regular $0.04 price). Output tokens are reported but not charged. This endpoint does not support chat completions, streaming, or tool calling.Start using Mercury Decide
Request examples, question types, response fields, and limits.
Our previous-generation reasoning model for fast chat, agents, and structured workflows.Export your API key as an environment variable in your terminal.
export INCEPTION_API_KEY="your_api_key_here"
set INCEPTION_API_KEY=your_api_key_here
$env:INCEPTION_API_KEY="your_api_key_here"
Example Usage
Chat Completions
v1/chat/completionscurl https://api.inceptionlabs.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $INCEPTION_API_KEY" \
-d '{
"model": "mercury-2.5",
"messages": [
{"role": "user", "content": "What is a diffusion model?"}
],
"reasoning_effort": "medium",
"max_completion_tokens": 8192
}'
from inceptionai import Inception
client = Inception() # reads INCEPTION_API_KEY from the environment
completion = client.chat.completions.create(
model="mercury-2.5",
messages=[{"role": "user", "content": "What is a diffusion model?"}],
reasoning_effort="medium",
max_completion_tokens=8192,
)
print(completion.choices[0].message.content)
import Inception from 'inceptionai';
const client = new Inception(); // reads INCEPTION_API_KEY from the environment
const completion = await client.chat.completions.create({
model: 'mercury-2.5',
messages: [{ role: 'user', content: 'What is a diffusion model?' }],
reasoning_effort: 'medium',
max_completion_tokens: 8192,
});
console.log(completion.choices[0]?.message.content);
An earlier-generation reasoning model for chat completions.Export your API key as an environment variable in your terminal.
export INCEPTION_API_KEY="your_api_key_here"
set INCEPTION_API_KEY=your_api_key_here
$env:INCEPTION_API_KEY="your_api_key_here"
Example Usage
Chat Completions
v1/chat/completionscurl https://api.inceptionlabs.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $INCEPTION_API_KEY" \
-d '{
"model": "mercury-2",
"messages": [
{"role": "user", "content": "What is a diffusion model?"}
],
"max_completion_tokens": 8192
}'
from inceptionai import Inception
client = Inception() # reads INCEPTION_API_KEY from the environment
completion = client.chat.completions.create(
model="mercury-2",
messages=[{"role": "user", "content": "What is a diffusion model?"}],
max_completion_tokens=8192,
)
print(completion.choices[0].message.content)
import Inception from 'inceptionai';
const client = new Inception(); // reads INCEPTION_API_KEY from the environment
const completion = await client.chat.completions.create({
model: 'mercury-2',
messages: [{ role: 'user', content: 'What is a diffusion model?' }],
max_completion_tokens: 8192,
});
console.log(completion.choices[0]?.message.content);
A code editing LLM for autocomplete (FIM) and next edit suggestions.Export your API key as an environment variable in your terminal.
export INCEPTION_API_KEY="your_api_key_here"
set INCEPTION_API_KEY=your_api_key_here
$env:INCEPTION_API_KEY="your_api_key_here"
Example Usage
Autocomplete (FIM)
v1/fim/completionscurl https://api.inceptionlabs.ai/v1/fim/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $INCEPTION_API_KEY" \
-d '{
"model": "mercury-edit-2",
"prompt": "def factorial(n):\n if n <= 1:\n return 1\n return n * ",
"suffix": "\n\nprint(factorial(5))",
"max_tokens": 1000
}'
from inceptionai import Inception
client = Inception() # reads INCEPTION_API_KEY from the environment
completion = client.fim.completions.create(
model="mercury-edit-2",
prompt="def factorial(n):\n if n <= 1:\n return 1\n return n * ",
suffix="\n\nprint(factorial(5))",
max_tokens=1000,
)
print(completion.choices[0].text)
import Inception from 'inceptionai';
const client = new Inception(); // reads INCEPTION_API_KEY from the environment
const completion = await client.fim.completions.create({
model: 'mercury-edit-2',
prompt: 'def factorial(n):\n if n <= 1:\n return 1\n return n * ',
suffix: '\n\nprint(factorial(5))',
max_tokens: 1000,
});
console.log(completion.choices[0]?.text);
Next-Edit
v1/edit/completionscurl https://api.inceptionlabs.ai/v1/edit/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $INCEPTION_API_KEY" \
--data-binary @- <<'JSON'
{
"model": "mercury-edit-2",
"messages": [
{"role": "user", "content": "<|recently_viewed_code_snippets|>\n\n<|/recently_viewed_code_snippets|>\n\n<|current_file_content|>\ncurrent_file_path: solver.py\n'''\nfunction: flagAllNeighbors\n----------\nThis function marks each of the covered neighbors of the cell at the given row\n<|code_to_edit|>\nand col as flagged.\n'''\ndef flagAllNeighbors(board<|cursor|>, row, col): \n for r, c in b.getNeighbors(row, col):\n if b.isValid(r, c):\n b.flag(r, c)\n\n<|/code_to_edit|>\n<|/current_file_content|>\n\n<|edit_diff_history|>\n--- /c:/Users/test/testing/solver.py\n+++ /c:/Users/test/testing/solver.py\n@@ -6,1 +6,1 @@\n-def flagAllNeighbors(b, row, col): \n+def flagAllNeighbors(board, row, col): \n\n<|/edit_diff_history|>"}
],
"max_tokens": 1000
}
JSON
from inceptionai import Inception
client = Inception() # reads INCEPTION_API_KEY from the environment
completion = client.edit.completions.create(
model="mercury-edit-2",
messages=[
{"role": "user", "content": "<|recently_viewed_code_snippets|>\n\n<|/recently_viewed_code_snippets|>\n\n<|current_file_content|>\ncurrent_file_path: solver.py\n'''\nfunction: flagAllNeighbors\n----------\nThis function marks each of the covered neighbors of the cell at the given row\n<|code_to_edit|>\nand col as flagged.\n'''\ndef flagAllNeighbors(board<|cursor|>, row, col): \n for r, c in b.getNeighbors(row, col):\n if b.isValid(r, c):\n b.flag(r, c)\n\n<|/code_to_edit|>\n<|/current_file_content|>\n\n<|edit_diff_history|>\n--- /c:/Users/test/testing/solver.py\n+++ /c:/Users/test/testing/solver.py\n@@ -6,1 +6,1 @@\n-def flagAllNeighbors(b, row, col): \n+def flagAllNeighbors(board, row, col): \n\n<|/edit_diff_history|>"}
],
max_tokens=1000,
)
print(completion.choices[0].message.content)
import Inception from 'inceptionai';
const client = new Inception(); // reads INCEPTION_API_KEY from the environment
const completion = await client.edit.completions.create({
model: 'mercury-edit-2',
messages: [
{ role: 'user', content: '<|recently_viewed_code_snippets|>\n\n<|/recently_viewed_code_snippets|>\n\n<|current_file_content|>\ncurrent_file_path: solver.py\n\'\'\'\nfunction: flagAllNeighbors\n----------\nThis function marks each of the covered neighbors of the cell at the given row\n<|code_to_edit|>\nand col as flagged.\n\'\'\'\ndef flagAllNeighbors(board<|cursor|>, row, col): \n for r, c in b.getNeighbors(row, col):\n if b.isValid(r, c):\n b.flag(r, c)\n\n<|/code_to_edit|>\n<|/current_file_content|>\n\n<|edit_diff_history|>\n--- /c:/Users/test/testing/solver.py\n+++ /c:/Users/test/testing/solver.py\n@@ -6,1 +6,1 @@\n-def flagAllNeighbors(b, row, col): \n+def flagAllNeighbors(board, row, col): \n\n<|/edit_diff_history|>' }
],
max_tokens: 1000,
});
console.log(completion.choices[0]?.message.content);
More Mercury Models
Mercury Voice
Built for responsive, real-time voice experiences.
Mercury Router
Match each request with the right Mercury model.
Explore all models
Learn more about the Mercury model family.