> ## Documentation Index > Fetch the complete documentation index at: https://apidocs.mor.org/llms.txt > Use this file to discover all available pages before exploring further. # Model Pricing > Pricing information for all models available through the Morpheus Inference API # Model Pricing All prices are per 1 million tokens in USD. ## Text Models
GLM 5.2 glm-5.2 Large 🧠 ⚡
Input Price \$1.25
Output Price \$4.40
Context 200K
Next-Gen Agentic Engineering and Complex Reasoning
GLM 5.1 glm-5.1 #16 Large 🧠 ⚡
Input Price \$1.50
Output Price \$5.00
Context 200K
Agentic Engineering and Complex Reasoning
Also available as glm-5.1-non-thinking (same pricing, without extended thinking)
GLM 5 glm-5 #25 Large 🧠 ⚡
Input Price \$1.00
Output Price \$3.20
Context 200K
Agentic Engineering and Complex Reasoning
Kimi K2.7 Code kimi-k2.7-code Large 🧠 ⚡
Input Price \$0.75
Output Price \$4.00
Context 256K
Code Generation, Agentic Coding, Parallel Agent Workflows
Kimi K2.5 kimi-k2.5 #32 Large 🧠 ⚡ 👀
Input Price \$0.60
Output Price \$3.00
Context 256K
Complex Agent Use and Code Development
Kimi K2.6 kimi-k2.6 Large 🧠 ⚡ 👀
Input Price \$0.50
Output Price \$3.25
Context 256K
Visual Reasoning, Math, Parallel Agent Workflows
Gemma 4 31B gemma-4-31b #29 Large 🧠 👀
Input Price \$0.15
Output Price \$0.40
Context 256K
Math, Science, Coding, Document Parsing, Visual Reasoning
Gemma 4 26B A4B gemma-4-26b-a4b #45 Large 🧠 👀
Input Price \$0.15
Output Price \$0.40
Context 256K
Efficient Reasoning, Low-Latency Inference, Image Analysis
Qwen 3.5 35B A3B qwen35-35b-a3b #102 Medium ⚡ 👀
Input Price \$0.30
Output Price \$1.25
Context 256K
General Purpose, Long Context, Image Analysis
Qwen 3.5 9B qwen35-9b Medium ⚡ 👀
Input Price \$0.05
Output Price \$0.15
Context 256K
Fast Responses, Image Analysis, Simple Tasks
Arcee Trinity Large Thinking arcee-trinity-large-thinking #123 Large 🧠 ⚡
Input Price \$0.30
Output Price \$1.00
Context 256K
Agentic Workflows, Multi-Step Planning, Tool Orchestration
GLM 4.7 glm-4.7 #42 Large âš¡
Input Price \$0.50
Output Price \$2.25
Context 198K
Complex Agent Use
GLM 4.7 Thinking glm-4.7-thinking #42 Large 🧠 ⚡
Input Price \$0.45
Output Price \$2.00
Context 198K
Complex Agent Use and Reasoning
GLM 4.7 Flash glm-4.7-flash #131 Large âš¡
Input Price \$0.10
Output Price \$0.50
Context 128K
Fast Advanced Agent Use
Qwen3 235B qwen3-235b #62 Large 🧠 ⚡
Input Price \$0.40
Output Price \$3.00
Context 128K
Advanced Agent Use and Code Development
MiniMax M2.5 minimax-m2.5 #95 Large 🧠 ⚡
Input Price \$0.30
Output Price \$1.20
Context 198K
AI Agents and Autonomous Workflows
MiniMax M2.7 MiniMax-M2.7 Large 🧠 ⚡
Input Price \$0.35
Output Price \$1.50
Context 198K
Cost-Efficient AI Agents and Autonomous Workflows
DeepSeek V4 Pro deepseek-v4-pro Large 🧠 ⚡
Input Price \$1.60
Output Price \$3.50
Context 1M
Frontier Reasoning, Complex Coding, Ultra-Long Context
DeepSeek V4 Flash deepseek-v4-flash Medium 🧠 ⚡
Input Price \$0.15
Output Price \$0.30
Context 1M
Fast Frontier-Tier Reasoning, Long-Context Tasks at Speed
Qwen3 Coder 480B qwen3-coder-480b-a35b-instruct #113 Large âš¡
Input Price \$0.70
Output Price \$2.80
Context 256K
Code Development
Qwen3 Next 80B qwen3-next-80b #93 Medium âš¡
Input Price \$0.15
Output Price \$1.50
Context 256K
Long-Context Chat and Content
GPT OSS 120B gpt-oss-120b #144 Large âš¡
Input Price \$0.07
Output Price \$0.28
Context 128K
Advanced Chat and Content
Hermes 3 Llama 3.1 405B hermes-3-llama-3.1-405b #172 Large
Input Price \$1.00
Output Price \$3.00
Context 128K
Advanced Chat and Content
Llama 3.3 70B llama-3.3-70b #193 Medium âš¡
Input Price \$0.70
Output Price \$2.50
Context 128K
General Chat and Content
Llama 3.2 3B llama-3.2-3b #295 Small âš¡
Input Price \$0.10
Output Price \$0.50
Context 128K
Classification, Simple QA
Mistral 31 24B mistral-31-24b #212 Medium ⚡ 👀
Input Price \$0.50
Output Price \$2.00
Context 128K
Basic Agent Functionality
Venice Uncensored venice-uncensored Medium
Input Price \$0.20
Output Price \$0.90
Context 32K
Uncensored Creative Use
## Proprietary, Anonymized Models Frontier proprietary models served through anonymized providers on the Morpheus marketplace. All are also available with web search by appending `:web` to the model name.
Claude Fable 5 claude-fable-5 Large
Input Price \$12.00
Output Price \$60.00
Frontier Agentic Coding and Reasoning
Claude Opus 4.8 claude-opus-4.8 Large
Input Price \$6.00
Output Price \$30.00
Advanced Reasoning and Code Development
Gemini 3.1 Pro Preview gemini-3.1-pro-preview Large
Input Price \$2.50
Output Price \$15.00
Multimodal Frontier Reasoning
GPT-5.5 Pro GPT-5.5-Pro Large
Input Price \$38.00
Output Price \$250.00
Maximum-Capability Frontier Reasoning
GPT-5.5 GPT-5.5 Large
Input Price \$6.50
Output Price \$38.00
Frontier Chat, Reasoning, and Coding
Grok 4.20 grok-4.20 Large
Input Price \$1.40
Output Price \$2.80
Fast, Cost-Efficient Frontier Intelligence
## Embedding Models
BGE M3 text-embedding-bge-m3 Embedding
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 * 👀 **Vision** — Can analyze and understand images * **Arena Rank** — Position on the [Chatbot Arena Leaderboard](https://lmarena.ai/) (lower is better)