Model Pricing
Understand how Verdent credits relate to provider token pricing and where to check current model rates
This page applies to both Verdent Desktop and Verdent for VS Code.
Overview
Verdent integrates state-of-the-art large language models from the world's leading AI labs, including Anthropic (Claude), OpenAI (GPT), Google (Gemini), Moonshot (Kimi), MiniMax, DeepSeek, Qwen, and Z.AI (GLM). To help users understand the cost behind every AI interaction, we disclose provider token pricing for Verdent's current built-in model lineup in this document.
All prices listed are provider-side published prices in US dollars ($) per one million tokens (1M tokens). The lineup was verified against Verdent's live model catalog on July 31, 2026.
Unless noted otherwise, the tables use each provider's paid, standard, short-context rate. Claude cache-write prices use the five-minute cache duration. A dash (-) means the provider does not publish a separate price for that component. Core pricing references include Anthropic, OpenAI, Google, Kimi, MiniMax, and DeepSeek.
Key Concepts
Tokens
A token is the fundamental unit of text processing for large language models. One token is approximately 4 English characters or 1-2 Chinese characters. Model pricing is based on the number of input and output tokens consumed, billed separately.
Billing Model
All models on Verdent currently use a per-token billing model, meaning you are charged based on the actual number of input and output tokens consumed during each interaction.
Price Components
Each model's pricing consists of the following dimensions:
- Input Price: The per-token cost for the prompt (user message and context) sent to the model.
- Output Price: The per-token cost for the response generated by the model. Typically higher than input price.
- Cache Write Price: Some models support prompt caching. This is the per-token cost when creating a cache entry for the first time.
- Cache Read Price: The per-token cost when hitting an existing cache entry. Typically much lower than the standard input price, effectively reducing costs for repeated contexts.
Model Pricing Details
Below are the provider prices for all models currently available on Verdent, organized by provider. All prices are in USD per 1M tokens.
Anthropic (Claude Series)
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| Claude Fable 5 | $10.00 | $50.00 | $12.50 | $1.00 |
| Claude Opus 5 | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.8 | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.7 | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.6 | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Sonnet 5 | $2.00 | $10.00 | $2.50 | $0.20 |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $3.75 | $0.30 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $1.25 | $0.10 |
Claude Sonnet 5 uses Anthropic's introductory price through August 31, 2026. Anthropic lists the standard price from September 1, 2026 as $3.00 input, $15.00 output, $3.75 cache write, and $0.30 cache read per 1M tokens.
Claude Fable 5 (claude-fable-5) Anthropic's highest-intelligence model for the hardest knowledge-work, coding, and agentic tasks.
Claude Opus 5 (claude-opus-5) Latest Opus model for difficult multi-file features, refactors, deep reasoning, and end-to-end agentic coding.
Claude Opus 4.8 (claude-opus-4-8) High-capability Opus model for complex coding, agentic tasks, enterprise workflows, and deep multi-step reasoning.
Claude Opus 4.7 (claude-opus-4-7) Opus model for long-running agents, multi-step coding tasks, and complex knowledge work.
Claude Opus 4.6 (claude-opus-4-6) Flagship-tier Opus model for complex code architecture, deep analysis, and difficult problem-solving tasks.
Claude Sonnet 5 (claude-sonnet-5) Latest Sonnet model with adaptive thinking for coding, agent planning, long-context analysis, and knowledge work.
Claude Sonnet 4.6 (claude-sonnet-4-6) Balanced model with strong performance and competitive pricing; recommended for everyday development.
Claude Haiku 4.5 (claude-haiku-4-5@20251001) Fast and lightweight model with low latency. Best for simple conversations, quick lookups, and cost-sensitive tasks.
OpenAI (GPT Series)
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| GPT-5.6 Sol | $5.00 | $30.00 | $6.25 | $0.50 |
| GPT-5.6 Terra | $2.00 | $12.00 | $2.50 | $0.20 |
| GPT-5.6 Luna | $0.20 | $1.20 | $0.25 | $0.02 |
| GPT-5.5 | $5.00 | $30.00 | - | $0.50 |
| GPT-5.4 | $2.50 | $15.00 | - | $0.25 |
| GPT-5.4 mini | $0.75 | $4.50 | - | $0.075 |
| GPT-5.3 Codex | $1.75 | $14.00 | - | $0.175 |
GPT-5.6 Sol (gpt-5.6-sol) Frontier GPT-5.6 model for the most demanding agentic coding and reasoning tasks.
GPT-5.6 Terra (gpt-5.6-terra) Balanced GPT-5.6 model for strong everyday coding, tool use, and reasoning at lower cost.
GPT-5.6 Luna (gpt-5.6-luna) Fast, highly cost-efficient GPT-5.6 model for routine development, subagents, and high-volume workflows.
GPT-5.5 (gpt-5.5) Frontier GPT model suited to reasoning, code generation, and multi-step analysis workloads.
GPT-5.4 (gpt-5.4) Flagship GPT model with strong reasoning and code generation quality.
GPT-5.4 mini (gpt-5.4-mini) Efficient GPT model for high-volume workloads, subagents, and cost-sensitive coding tasks.
GPT-5.3 Codex (gpt-5.3-codex) Code-specialized model optimized for programming tasks, including large-scale code generation and refactoring.
Google (Gemini Series)
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| Gemini 3.6 Flash | $1.50 | $7.50 | - | $0.15 |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | - | $0.03 |
| Gemini 3.1 Pro | $2.00 | $12.00 | - | $0.20 |
| Gemini 3 Flash | $0.50 | $3.00 | - | $0.05 |
Gemini 3.6 Flash (gemini-3.6-flash) Fast frontier Gemini model with improved coding, knowledge, multimodal understanding, and token efficiency.
Gemini 3.5 Flash-Lite (gemini-3.5-flash-lite) Cost-efficient Gemini model for high-throughput agentic execution and lightweight workloads.
Gemini 3.1 Pro (gemini-3.1-pro-preview) Professional-grade model with strong reasoning, suitable for complex analysis and deep thinking tasks.
Gemini 3 Flash (gemini-3-flash-preview) Ultra-fast model with excellent cost efficiency. Ideal for high-volume batch processing.
Moonshot (Kimi Series)
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| Kimi K3 | $3.00 | $15.00 | - | $0.30 |
| Kimi K2.7 Code | $0.95 | $4.00 | - | $0.19 |
Kimi K3 (kimi-k3) Moonshot's most capable coding model, with stronger long-context reliability for complex agentic workflows.
Kimi K2.7 Code (kimi-k2.7-code) Coding-focused Kimi model built for long-context programming tasks and agentic code workflows.
MiniMax
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| MiniMax M3 | $0.60 | $2.40 | - | $0.12 |
MiniMax M3 (MiniMax-M3) Cost-efficient long-context model for reliable multi-skill agent workflows, engineering tasks, and office automation.
DeepSeek
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| DeepSeek V4 Pro | $0.435 | $0.87 | - | $0.003625 |
DeepSeek V4 Pro (deepseek-v4-pro) Advanced model for mathematical and logical reasoning, coding, and long-context analysis.
Qwen
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| Qwen3.7-Plus | $0.1794 | $0.7157 | $0.00 | $0.0364 |
Qwen3.7-Plus (qwen3.7-plus) Cost-effective multimodal model for text, image, and video inputs, with strong agentic and vision-language capabilities.
Z.AI (GLM Series)
| Model | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|
| GLM-5.2 | $1.40 | $4.40 | - | $0.26 |
GLM-5.2 (glm-5.2) Long-context engineering model for project-scale code understanding, stable long-task execution, and standards-aware implementation work.
Pricing Overview
The table below summarizes the core pricing for all currently enabled models, sorted by output price descending for easy comparison:
| Model | Provider | Input ($/1M) | Output ($/1M) | Cache Write ($/1M) | Cache Read ($/1M) |
|---|---|---|---|---|---|
| Claude Fable 5 | Anthropic | $10.00 | $50.00 | $12.50 | $1.00 |
| GPT-5.6 Sol | OpenAI | $5.00 | $30.00 | $6.25 | $0.50 |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | - | $0.50 |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.8 | Anthropic | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | $6.25 | $0.50 |
| Claude Opus 4.6 | Anthropic | $5.00 | $25.00 | $6.25 | $0.50 |
| GPT-5.4 | OpenAI | $2.50 | $15.00 | - | $0.25 |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | $3.75 | $0.30 |
| Kimi K3 | Moonshot | $3.00 | $15.00 | - | $0.30 |
| GPT-5.3 Codex | OpenAI | $1.75 | $14.00 | - | $0.175 |
| GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | $2.50 | $0.20 |
| Gemini 3.1 Pro | $2.00 | $12.00 | - | $0.20 | |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | $2.50 | $0.20 |
| Gemini 3.6 Flash | $1.50 | $7.50 | - | $0.15 | |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | $1.25 | $0.10 |
| GPT-5.4 mini | OpenAI | $0.75 | $4.50 | - | $0.075 |
| GLM-5.2 | Z.AI | $1.40 | $4.40 | - | $0.26 |
| Kimi K2.7 Code | Moonshot | $0.95 | $4.00 | - | $0.19 |
| Gemini 3 Flash | $0.50 | $3.00 | - | $0.05 | |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | - | $0.03 | |
| MiniMax M3 | MiniMax | $0.60 | $2.40 | - | $0.12 |
| GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | $0.25 | $0.02 |
| DeepSeek V4 Pro | DeepSeek | $0.435 | $0.87 | - | $0.003625 |
| Qwen3.7-Plus | Qwen | $0.1794 | $0.7157 | $0.00 | $0.0364 |