> ## Documentation Index
> Fetch the complete documentation index at: https://docs.relace.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Apply Code
> Merge code snippets from an LLM into your existing codebase.
Relace apply runs at over 10,000 tok/s, making complicated code merges feel instantaneous.
## Models
We have deprecated all previous versions of the apply models in favor of `relace-apply-3`, which is more performant on accuracy, speed, and long context requests.
| Model | Speed | Max Input | Max Output |
| :--------------- | :------------- | :---------- | :---------- |
| `relace-apply-3` | \~10k tokens/s | 128k tokens | 128k tokens |
## OpenAI Compatible Endpoint
If the Relace REST API is inconvenient, we also support an OpenAI compatible endpoint for our apply models.
```typescript theme={null}
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://instantapply.endpoint.relace.run/v1/apply',
});
const userMessage = `
{instruction}
{initial_code}
{edit_snippet}
`;
const response = await client.chat.completions.create({
model: 'auto',
messages: [
{
role: 'user',
content: userMessage,
},
],
});
```
The user message must include `` and `` tags following the format above. The `` tag is optional.
### OpenRouter
Relace Apply is also available via OpenRouter's OpenAI-compatible endpoint. See the [model page](https://openrouter.ai/relace/relace-apply-3) for current availability and details.
The [performance](https://openrouter.ai/relace/relace-apply-3/performance) section of the model page shows our real-time throughput and latency numbers from customer requests.
## Fallbacks
We recommend using GPT-4.1-mini with [predictive edits](https://platform.openai.com/docs/guides/predicted-outputs) as a fallback. This option is 10-20x slower than Relace's apply models, but it's useful for redundancy.
Relace apply models also return a `400` error code when input exceeds context limits (see table above). For these cases, GPT-4o-mini's 1M token context window is a reliable fallback option.
However, even frontier LLMs struggle with long context. We recommend proactive refactoring of files >32k tokens to improve output quality.
## OpenAPI
````yaml POST /v1/code/apply
openapi: 3.0.1
info:
title: Relace API
description: API for accessing Relace code generation models.
version: 1.0.0
license:
name: MIT
servers:
- url: https://instantapply.endpoint.relace.run
description: Server for code application endpoints
- url: https://ranker.endpoint.relace.run
description: Server for code ranking endpoints
- url: https://embeddings.endpoint.relace.run
description: Server for code embedding endpoints
- url: https://api.relace.run
description: Server for general infrastructure
security:
- bearerAuth: []
paths:
/v1/code/apply:
post:
description: Merge code snippets from an LLM into your existing codebase.
requestBody:
description: Initial code and edits to apply
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/InstantApplyRequest'
example:
initial_code: |-
function calculateTotal(items) {
let total = 0;
for (const item of items) {
total += item.price * item.quantity;
}
return total;
}
edit_snippet: |-
// ... keep existing code
function applyDiscount(total, discountRules) {
let discountedTotal = total;
if (discountRules.percentOff) {
discountedTotal -= (total * discountRules.percentOff / 100);
}
if (discountRules.fixedAmount && discountRules.fixedAmount < discountedTotal) {
discountedTotal -= discountRules.fixedAmount;
}
return Math.max(0, discountedTotal);
}
stream: false
responses:
'200':
description: Code successfully applied
content:
application/json:
schema:
$ref: '#/components/schemas/InstantApplyResponse'
text/event-stream:
schema:
type: string
description: >-
Stream of results from the Instant Apply model (compatible
with OpenAI streaming format)
'400':
description: Bad request
content:
application/json:
schema:
$ref: '#/components/schemas/Error400'
'401':
description: Unauthorized
content:
application/json:
schema:
$ref: '#/components/schemas/Error401'
'404':
description: API key not found
content:
application/json:
schema:
$ref: '#/components/schemas/Error404'
'429':
description: Rate limit exceeded
headers:
X-RateLimit-Limit:
schema:
type: string
description: Rate limit ceiling for the API key
X-RateLimit-Remaining:
schema:
type: string
description: Number of requests left for the time window
X-RateLimit-Reset:
schema:
type: string
description: Time at which the rate limit resets
content:
application/json:
schema:
$ref: '#/components/schemas/Error429'
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/Error500'
servers:
- url: https://instantapply.endpoint.relace.run
components:
schemas:
InstantApplyRequest:
type: object
required:
- initial_code
- edit_snippet
properties:
model:
type: string
description: Choice of apply model to use
enum:
- relace-apply-3
default: relace-apply-3
initial_code:
type: string
description: The original code that needs to be modified
edit_snippet:
type: string
description: The code changes to be applied to the initial code
instruction:
type: string
description: >-
Optional single line instruction for to disambiguate the edit
snippet. *e.g.* `Remove the captcha from the login page`
stream:
type: boolean
description: Whether to stream the response back
default: false
relace_metadata:
type: object
description: Optional metadata for logging and tracking purposes.
additionalProperties: true
InstantApplyResponse:
type: object
properties:
mergedCode:
type: string
description: The merged code with the changes applied
usage:
type: object
properties:
prompt_tokens:
type: integer
description: Number of tokens in the prompt
completion_tokens:
type: integer
description: Number of tokens in the completion
total_tokens:
type: integer
description: Total number of tokens used
description: Token usage information for the request
example:
mergedCode: |-
function calculateTotal(items) {
let total = 0;
for (const item of items) {
total += item.price * item.quantity;
}
return total;
}
function applyDiscount(total, discountRules) {
let discountedTotal = total;
if (discountRules.percentOff) {
discountedTotal -= (total * discountRules.percentOff / 100);
}
if (discountRules.fixedAmount && discountRules.fixedAmount < discountedTotal) {
discountedTotal -= discountRules.fixedAmount;
}
return Math.max(0, discountedTotal);
}
usage:
prompt_tokens: 245
completion_tokens: 187
total_tokens: 432
Error400:
type: object
properties:
error:
type: string
description: Error message
example: Invalid JSON in request body
Error401:
type: object
properties:
error:
type: string
description: Error message
example: Authorized header required
Error404:
type: object
properties:
error:
type: string
description: Error message
example: 'Bad Request: Route not found'
Error429:
type: object
properties:
error:
type: string
description: Error message
example: Rate limit exceeded
Error500:
type: object
properties:
error:
type: string
description: Error message
example: Error fetching from origin server
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Relace API key Authorization header using the Bearer scheme.
````