Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Inception / Mercury

Mercury Edit 2

Proprietary diffusion language model from Inception.

Language models (LLMs)
restrictedClosed weightsCoding
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
10 of 17 specification fields collected
Context window32K32,000 tokens
Maximum output8.2K8,192 tokens
Input / 1M tokens$0.25Inception API
Output / 1M tokens$0.75USD · observed 15 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
32,000 tokensSource for Context / input limit (opens in a new tab)

Endpoint-specific guide says 32K; live discovery instead reports 128,000. The conflict remains unresolved.

Maximum input tokens
Not collected

No exact model-specific contract established in the reviewed evidence.

Maximum output
8,192 tokensSource for Maximum output (opens in a new tab)

Both FIM and edit request schemas cap max_tokens at 8,192; discovery instead reports 32,000. Endpoint request contract is used here.

Parameters
Not collected

No exact model-specific contract established in the reviewed evidence.

Release date
2026-03-30Source for Release date (opens in a new tab)
Knowledge cutoff
Not collected

No exact model-specific contract established in the reviewed evidence.

Reasoning
Not collected

No exact model-specific contract established in the reviewed evidence.

Tool calling
Not supportedSource for Tool calling (opens in a new tab)

Both supported endpoints explicitly exclude tool calling.

Structured output
Not collected

No exact model-specific contract established in the reviewed evidence.

Streaming
SupportedSource for Streaming (opens in a new tab)

FIM supports streaming. Next-edit does not.

Batch processing
Not collected

No exact model-specific contract established in the reviewed evidence.

Fine-tuning
Not collected

No exact model-specific contract established in the reviewed evidence.

Context caching
SupportedSource for Context caching (opens in a new tab)

Automatic prefix caching; no documented TTL guarantee.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Architecture
Diffusion language model using parallel iterative refinement.Source for Architecture (opens in a new tab)

Exact parameter count and layer architecture are not published here.

Published training method
Curated code edits followed by human preference feedback on accepting or rejecting suggestions.Source for Published training method (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Inception API

Provider source (opens in a new tab)
API model ID
mercury-edit-2
Access
API key required. The documented task-specific request limits are used pending resolution of discovery metadata conflicts.
Regions
US listed by model discovery; exact residency commitments are contractual.
API endpoint
POST /v1/fim/completionsSource for API endpoint (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Public API only.

Generation controls
Prefix prompt plus optional suffix; default output budget 512.Source for Generation controls (opens in a new tab)
INPUT / 1M TOKENS$0.25
OUTPUT / 1M TOKENS$0.75

Published current endpoint tariff. Billed output includes reasoning where applicable. Cached input price: $0.025 / 1M tokens (base tier).

USD · observed 15 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Cache chargesAdditional cache write rate1$0.001M tokens

Rate conditions

  1. The discovery response lists input_cache_writes as zero. This does not remove ordinary input charges or guarantee cache reuse.
Pricing source (opens in a new tab)

Data & enterprise terms

Terms permit using submissions for model training unless the user disables “Improve the model for everyone” in API Platform settings. The privacy policy uses purpose-dependent retention, not a fixed universal period. The FAQ says custom zero-retention arrangements are handled case by case; enterprise agreements may differ.

Read the service policy (opens in a new tab)

Inception API

Provider source (opens in a new tab)
API model ID
mercury-edit-2
Access
API key required. The documented task-specific request limits are used pending resolution of discovery metadata conflicts.
Regions
US listed by model discovery; exact residency commitments are contractual.
API endpoint
POST /v1/edit/completionsSource for API endpoint (opens in a new tab)
Streaming
Not supportedSource for Streaming (opens in a new tab)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)

Public API only.

Generation controls
One user message with required code/cursor/file tags. Default output budget 1,024; temperature 0–2, default 0.2.Source for Generation controls (opens in a new tab)
INPUT / 1M TOKENS$0.25
OUTPUT / 1M TOKENS$0.75

Published current endpoint tariff. Billed output includes reasoning where applicable. Cached input price: $0.025 / 1M tokens (base tier).

USD · observed 15 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Cache chargesAdditional cache write rate1$0.001M tokens

Rate conditions

  1. The discovery response lists input_cache_writes as zero. This does not remove ordinary input charges or guarantee cache reuse.
Pricing source (opens in a new tab)

Data & enterprise terms

Terms permit using submissions for model training unless the user disables “Improve the model for everyone” in API Platform settings. The privacy policy uses purpose-dependent retention, not a fixed universal period. The FAQ says custom zero-retention arrangements are handled case by case; enterprise agreements may differ.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Inception API

mercury-edit-2
Documented
Support evidence (opens in a new tab)
How it works
Automatic prefix caching.Source for How it works (opens in a new tab)
Minimum reusable input
Not collected

Minimum prefix length not documented.

Lifetime & refresh
No documented TTL; pinning, invalidation and cache inspection are not exposed.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Enabled automatically; no request parameter required.Source for How to enable it (opens in a new tab)
Usage fields
prompt_tokens includes cached_tokens; completion_tokens includes reasoning_tokens. Do not add nested counts again. Streaming usage requires stream_options.include_usage.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the model-specific cached-input rate. Reasoning tokens are billed as output.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Cache lifetime is not a customer-data-retention promise.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.025 / 1M tokensPricing evidence (opens in a new tab)
Additional cache write rate2Cache charges$0.00 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Published current endpoint tariff. Billed output includes reasoning where applicable.
  2. The discovery response lists input_cache_writes as zero. This does not remove ordinary input charges or guarantee cache reuse.

Observed 15 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 15 Oct 2026

Inception API

mercury-edit-2
Documented
Support evidence (opens in a new tab)
How it works
Automatic prefix caching.Source for How it works (opens in a new tab)
Minimum reusable input
Not collected

Minimum prefix length not documented.

Lifetime & refresh
No documented TTL; pinning, invalidation and cache inspection are not exposed.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Enabled automatically; no request parameter required.Source for How to enable it (opens in a new tab)
Usage fields
prompt_tokens includes cached_tokens; completion_tokens includes reasoning_tokens. Do not add nested counts again. Streaming usage requires stream_options.include_usage.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the model-specific cached-input rate. Reasoning tokens are billed as output.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Cache lifetime is not a customer-data-retention promise.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.025 / 1M tokensPricing evidence (opens in a new tab)
Additional cache write rate2Cache charges$0.00 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Published current endpoint tariff. Billed output includes reasoning where applicable.
  2. The discovery response lists input_cache_writes as zero. This does not remove ordinary input charges or guarantee cache reuse.

Observed 15 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inception’s own Trust Center describes the Mercury family as proprietary. Public API and enterprise deployment access do not establish public weights.

Classification evidence (opens in a new tab)

Sources reviewed