Apply 3
Apply 3 is Relace's language model with a 256K context window and up to 128K output tokens, starting at $0.850 / 1M input and $1.25 / 1M output. A specialized code-patching LLM that merges AI-suggested edits directly into source files, compatible with outputs from GPT-4o, Claude, and other models.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.850 | $1.25 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Apply 3 | 256K | $0.850 | $1.25 | Current | |
| Relace Search | 256K | $1.00 | $3.00 | Available |