impulse

Mercury Edit 2

API id mercury-edit-2
Input / 1M
$0.25
at Text Completion Inception
Output / 1M
$0.75
at Text Completion Inception
Context window
32K
tokens
Max output
8K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Text Completion Inception, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.25$0.75
Cached input
90% off input
$0.025

What it costs a month

At Text Completion Inception list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$111
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$93.00
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$156
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$780
Use your own numbers

Where to run it

1 host serve Mercury Edit 2. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
mercury-edit-2
$0.25 / $0.75

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Text Completion Inception.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    47% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    47% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    30% less

Open-weight picks

Call it

Using Text Completion Inception's API.

Python
from litellm import completion

response = completion(
    model="text-completion-inception/mercury-edit-2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mercury Edit 2 cost?

On Text Completion Inception, Mercury Edit 2 costs $0.25 per million input tokens and $0.75 per million output tokens. Cached input costs $0.025 per million tokens.

Which APIs offer Mercury Edit 2?

Mercury Edit 2 runs on 1 API: Text Completion Inception.

What is Mercury Edit 2's context window?

32K tokens, with up to 8K tokens in one reply.

Is Mercury Edit 2 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mercury Edit 2?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (47% less), GPT-6 Luna on OpenAI (47% less) and Qwen3.5 397B A17B on AIHubMix (1% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Mercury Edit 2's API model id?

Use mercury-edit-2 with Text Completion Inception.

Sources

Raw catalog entry for mercury-edit-2 on Text Completion Inception
{
  "cache_read_input_token_cost": 2.5e-8,
  "input_cost_per_token": 2.5e-7,
  "litellm_provider": "text-completion-inception",
  "max_input_tokens": 32000,
  "max_output_tokens": 8192,
  "mode": "completion",
  "output_cost_per_token": 7.5e-7
}