Skip to main content

​
Model Pricing

All prices are per 1 million tokens in USD.
Open Beta: The Morpheus Inference API is currently FREE during the Open Beta program. The pricing below will take effect after the beta period ends.

​
Text Models

Kimi K2.5kimi-k2.5#12Large
Input Price$0.60
Output Price$3.00
Context256K
Complex Agent Use and Code Development
Kimi K2 Thinkingkimi-k2-thinking#27Large
Input Price$0.60
Output Price$3.00
Context256K
Complex Agent Use and Code Development
GLM 4.7glm-4.7#19Large
Input Price$0.50
Output Price$2.25
Context198K
Complex Agent Use
GLM 4.7 Thinkingglm-4.7-thinking#19Large
Input Price$0.50
Output Price$2.25
Context198K
Complex Agent Use and Reasoning
GLM 4.7 Flashglm-4.7-flash#97Large
Input Price$0.13
Output Price$0.50
Context128K
Fast Advanced Agent Use
Qwen3 235Bqwen3-235b#59Large
Input Price$0.40
Output Price$3.00
Context128K
Advanced Agent Use and Code Development
Qwen3 Coder 480Bqwen3-coder-480b-a35b-instruct#77Large
Input Price$0.70
Output Price$2.80
Context256K
Code Development
Qwen3 Next 80Bqwen3-next-80b#60Medium
Input Price$0.25
Output Price$1.75
Context256K
Long-Context Chat and Content
Qwen3 4Bqwen3-4bSmall
Input Price$0.05
Output Price$0.15
Context32K
Classification, Simple QA
GPT OSS 120Bgpt-oss-120b#103Large
Input Price$0.07
Output Price$0.28
Context128K
Advanced Chat and Content
Hermes 3 Llama 3.1 405Bhermes-3-llama-3.1-405b#127Large
Input Price$1.00
Output Price$2.75
Context128K
Advanced Chat and Content
Llama 3.3 70Bllama-3.3-70b#149Medium
Input Price$0.70
Output Price$2.50
Context128K
General Chat and Content
Llama 3.2 3Bllama-3.2-3b#253Small
Input Price$0.10
Output Price$0.35
Context128K
Classification, Simple QA
Mistral 31 24Bmistral-31-24b#170Medium
Input Price$0.50
Output Price$2.00
Context128K
Basic Agent Functionality
Venice Uncensoredvenice-uncensoredMedium
Input Price$0.20
Output Price$0.90
Context32K
Uncensored Creative Use

​
Embedding Models

BGE M3text-embedding-bge-m3Embedding
Input Price$0.10
Output Price$0.50
Vector Embeddings for RAG

​
Legend

  • 🧠 Reasoning — Extended thinking and step-by-step problem solving
  • ⚡ Function Calling — Can invoke tools and external APIs
  • Arena Rank — Position on the Chatbot Arena Leaderboard (lower is better)