Morph · Language model

Morph V3 Large

morph/morph-v3-large

Language

Released Jul 7, 2025

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

Specifications

Context window: 262,144 tokens
Max output: 131,072 tokens
Input: text
Output: text
Tokenizer: Other

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

logprobs
max_tokens
response_format
stop
structured_outputs
temperature
top_logprobs

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"morph/morph-v3-large","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'