Relace Apply 3
3445°
Run this model
Offers / Ads
Relace | 256,000 token context | $0.85/M input, $1.25/M output. Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet} Zero Data Retention is enabled for Relace. Learn more about this model in their documentationOpens in new tab
Guides for this model
Open weights vs open source vs API-only: what you are actually allowed to do
The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans
Captain's notes
Notes from 2026-10-13
Relace Apply 3 is a closed-weights model from Relace built for one job: taking an AI-generated code suggestion and merging it cleanly into your existing source files. It accepts edits from GPT-4o, Claude, and other models and applies them at roughly 10,000 tokens per second. If your workflow involves a frontier model for reasoning and a fast, cheap applier for the actual file writes, this is built for that split.
Known for
- Applies AI-suggested code edits directly into source files at ~10,000 tokens/sec
- Works with suggestions from GPT-4o, Claude, and other upstream models
- 256,000-token context window handles large files and multi-file patches
- Zero data retention policy — your code is not stored
- Priced below $1.25/M output, making high-volume patching affordable
Watch out for
- Closed weights, API-only — you cannot run this locally or inspect the model
- Requires a strict prompt format: instruction, initial code, then edit snippet — deviating breaks it
- Single-purpose: not a general coding assistant, reasoning model, or chat model
Prompts to try
Apply a refactor suggestion
Refactor the following function to use async/await instead of callbacks.
def fetch_data(url, callback):
response = requests.get(url)
callback(response.json())
async def fetch_data(url):
async with aiohttp.ClientSession() as session:
async with session.get(url) as response:
return await response.json()
Patch a bug fix into code
Fix the off-by-one error in the loop.
for i in range(0, len(items) - 1):
process(items[i])
for i in range(0, len(items)):
process(items[i])
Add error handling to a function
Add try/except error handling around the file read operation.
def read_config(path):
with open(path) as f:
return json.load(f)
def read_config(path):
try:
with open(path) as f:
return json.load(f)
except (FileNotFoundError, json.JSONDecodeError) as e:
raise RuntimeError(f'Failed to read config: {e}')
Compare with
- Kokoro-82MOpen-weights model
- Mistral 7B Instruct v0.2Open-weights model32,768 token context · $0.06/M input, $0.06/M output
- Mistral Small 3.2 24B Instruct 2506Open-weights model128,000 token context · $0.07/M input, $0.20/M output
- DeepSeek V3Open-weights model163,840 token context · $0.32/M input, $0.89/M output
More text models from relace
Questions people ask
- Can I run Relace Apply 3 locally?
- No — it is a closed-weights, API-only model. There are no public weights and no Hugging Face repository.
- What does it cost and how large is the context?
- Relace Apply 3 costs $0.85 per million input tokens and $1.25 per million output tokens, with a 256,000-token context window.
- How is this different from just asking Claude or GPT-4o to edit my code?
- Relace Apply 3 is not a reasoning model — it takes an edit snippet already produced by another model and merges it into your source file at high speed, acting as a fast, cheap applier in a two-step pipeline.
Captain's verdictA narrow tool that does one thing well: if you already have an AI-generated diff, this applies it fast and cheaply.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Relace Apply 3 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153