Pricing

We offer a range of pricing options to suit your needs.

Fast Apply Models

morph-v3-fast
Fastest model
4500+ tok/sec
16k input tokens, 16k output tokens
Input:
$0.8/1M tokens
Output:
$1.2/1M tokens
morph-v3-large
Most capable
2500+ tok/sec
16k input tokens, 16k output tokens
Input:
$0.9/1M tokens
Output:
$1.9/1M tokens
auto
Smart routing
2500-4500 tok/sec
Based on selected model
Need Larger Context Lengths?Handle larger files and contexts

Embedding Model

morph-embedding-v2
High-precision code search
$0.18/1M tokens

Reranking Model

morph-rerank-v2
Context-aware results
$0.80/1M tokens