How do I use Morph models through the OpenRouter API?

OpenRouter serves 6 Morph models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as morph/reflex. The quickstart has request examples for every supported SDK.

Which Morph model has the largest context window?

Morph V3 Large has the largest context window of any Morph model on OpenRouter, accepting up to 262,144 tokens per request.

What is the newest Morph model on OpenRouter?

Reflex is the most recently added Morph model on OpenRouter, listed on November 3, 2026.

Morph

Access 6 Morph models through the OpenRouter unified API including Reflex, Morph V3 Large, and Morph V3 Large (batch). Compare pricing, context windows, benchmarks, and capabilities between different Morph models.

Morph tokens processed on OpenRouter

Morph: ReflexReflex
3.16B tokens
Morph's decision model. Answers typed choice, noul and score questions about a state. The state is prefix-cached across requests, so repeat questions on the same state bill at the cached-input rate. 65k context window.
by morphNov 3, 2026$0.042/M input tokens$0/M output tokens
Morph: Morph V3 LargeMorph V3 Large
52.6M tokens
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> <update>{edit_snippet}</update> Zero Data Retention is enabled for Morph. Learn more about this model in their documentation
by morphJul 7, 2025262K context$0.90/M input tokens$1.90/M output tokens
Morph: Morph V3 Large (batch)Morph V3 Large (batch)
133K tokens
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> <update>{edit_snippet}</update> Zero Data Retention is enabled for Morph. Learn more about this model in their documentation
by morphJul 7, 2025262K context$0.45/M input tokens$0.95/M output tokens
Morph: Morph V3 FastMorph V3 Fast
86.6M tokens
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> Zero Data Retention is enabled for Morph. Learn more about this model in their documentation
by morphJul 7, 2025262K context$0.80/M input tokens$1.20/M output tokens
Morph: Morph V3 Fast (batch)Morph V3 Fast (batch)
428K tokens
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> Zero Data Retention is enabled for Morph. Learn more about this model in their documentation
by morphJul 7, 202582K context$0.40/M input tokens$0.60/M output tokens
Morph: Fast ApplyFast Apply
Morph Apply is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 4000+ tokens per second. The model requires the prompt to be in the following format: <code>${originalCode}</code>\n<update>${updateSnippet}</update> Learn more about this model in their documentation
by morphJun 26, 202532K context

Morph

Documentation

Frequently asked questions