---
id: "morph/morph-v3-fast"
also: ["morph/morph-v3-fast", "vercel/morph/morph-v3-fast"]
card_usd_per_m: "0.8 in, 1.2 out, at morph"
cheapest_list_usd_per_m: "0.8 in, 1.2 out, at morph on openrouter"
cheapest_effective_usd_per_m: "0.7999 in, 1.1999 out, at morph/fp8 on openrouter"
context: 262144
max_output: 131072
input: ["text"]
output: ["text"]
released: "2025-07-07"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["logprobs", "max_tokens", "response_format", "stop", "structured_outputs", "temperature", "top_logprobs"]
endpoints: 3
gateways: "openrouter (2), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Morph: Morph V3 Fast

Morph's fastest apply model for code edits. \~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial\_code}</code> <update>{edit\_snippet}</update>...