---
title: "What are message tokens? - Chat Thing Documentation"
canonical_url: "https://chatthing.ai/docs/what-are-message-tokens"
last_updated: "2026-07-13T16:51:24.733Z"
meta:
  description: "Understand message tokens and how they are used for different models."
  "og:description": "Understand message tokens and how they are used for different models."
  "og:title": "What are message tokens?"
  "twitter:description": "Understand message tokens and how they are used for different models."
  "twitter:title": "What are message tokens?"
---

**Usage and billing**

# What are message tokens?

Message tokens are used each time you send a message to a bot and receive a response. Each message uses between **1000** and **4000** message tokens (but can be more), depending on the questions and the bot's response. This means **200,000** message tokens roughly equate to **100** messages.

Generally, as a conversation gets longer, more message tokens will be used for each message as the entire chat history is sent to the model each time.

## Models and message tokens

Depending on the model you choose for your bot, the number of message tokens used will be calculated differently. This allows us to standardise the cost of the available models compared to the GPT 3.5 Turbo model. The token multipliers for each model are listed below:

### **Anthropic**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Claude Haiku 3 | **x 0.5** | **x 2.5** |
| Claude Haiku 3.5 | **x 1.6** | **x 8** |
| Claude Haiku 4.5 | **x 2** | **x 10** |
| Claude Sonnet 5 | **x 4** | **x 20** |
| Claude Sonnet 3.7 | **x 6** | **x 30** |
| Claude Sonnet 4 | **x 6** | **x 30** |
| Claude Sonnet 4.5 | **x 6** | **x 30** |
| Claude Sonnet 4.6 | **x 6** | **x 30** |
| Claude Opus 4.8 | **x 10** | **x 50** |
| Claude Opus 4.5 | **x 10** | **x 50** |
| Claude Opus 4.6 | **x 10** | **x 50** |
| Claude Opus 4.7 | **x 10** | **x 50** |
| Claude Sonnet 3.5 | **x 12** | **x 60** |
| Claude Opus 4.8 (Fast) | **x 20** | **x 100** |
| Claude Opus 4 | **x 30** | **x 150** |
| Claude Opus 4.1 | **x 30** | **x 150** |
| Claude Opus 4.7 (Fast) | **x 60** | **x 300** |

### **Cohere**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Cohere - Command R | **x 0.3** | **x 1.2** |
| Cohere - Command R+ | **x 5** | **x 20** |

### **DeepSeek**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| DeepSeek V4 Flash | **x 0.18** | **x 0.36** |
| DeepSeek V3 | **x 0.6** | **x 2.4** |
| DeepSeek V4 Pro | **x 0.87** | **x 1.74** |
| DeepSeek R1 | **x 1.4** | **x 4.8** |

### **Google**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Google - Gemini 2 Flash Lite | **x 0.15** | **x 0.6** |
| Google - Gemini 2.5 Flash Lite | **x 0.2** | **x 0.8** |
| Google - Gemini 2 Flash | **x 0.2** | **x 0.8** |
| Gemini 3.1 Flash Lite | **x 0.5** | **x 3** |
| Google - Gemini 2.5 Flash | **x 0.6** | **x 5** |
| Google - Gemini 3 Flash | **x 1** | **x 6** |
| Google - Gemini 2.5 Pro | **x 2.5** | **x 20** |
| Gemini 3.5 Flash | **x 3** | **x 18** |
| Google - Gemini 3 Pro | **x 4** | **x 24** |

### **Meta**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Llama 4 Scout | **x 0.16** | **x 0.6** |
| Llama 4 Maverick | **x 0.3** | **x 1.2** |

### **Mistral**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Mistral - Mistral Small | **x 0.06** | **x 0.22** |
| Mistral - Open Mistral 7b | **x 0.06** | **x 0.11** |
| Mistral - Open Mixtral 8x7b | **x 1.08** | **x 1.08** |
| Mistral Medium 3.5 | **x 3** | **x 15** |
| Mistral - Mistral Large | **x 4** | **x 12** |
| Mistral - Open Mixtral 8x22b | **x 4** | **x 12** |

### **MoonshotAI**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Kimi K2 | **x 1** | **x 4.8** |
| Kimi K2.6 | **x 1.36** | **x 6.82** |

### **OpenAI**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| GPT-5 Nano | **x 0.1** | **x 0.8** |
| GPT-4.1 Nano | **x 0.2** | **x 0.8** |
| GPT-4o Mini our**default** | **x 0.3** | **x 1.2** |
| GPT-5.4 Nano | **x 0.4** | **x 2.5** |
| GPT-5 Mini | **x 0.5** | **x 4** |
| GPT-4.1 Mini | **x 0.8** | **x 3.2** |
| GPT-3.5 Turbo | **x 1** | **x 3** |
| GPT-5.4 Mini | **x 1.5** | **x 9** |
| GPT-5.6 Luna | **x 2** | **x 12** |
| GPT-5.6 Luna Pro | **x 2** | **x 12** |
| GPT-5.1 | **x 2.5** | **x 20** |
| GPT-5.1 Chat | **x 2.5** | **x 20** |
| GPT-5 | **x 2.5** | **x 20** |
| GPT-5.2 | **x 3.5** | **x 28** |
| GPT-4.1 | **x 4** | **x 16** |
| GPT-5.6 Terra | **x 5** | **x 30** |
| GPT-5.6 Terra Pro | **x 5** | **x 30** |
| GPT-5.4 | **x 5** | **x 30** |
| GPT-4o | **x 5** | **x 20** |
| GPT-5.6 Sol | **x 10** | **x 60** |
| GPT-5.6 Sol Pro | **x 10** | **x 60** |
| GPT-5.5 | **x 10** | **x 60** |
| GPT-4 Turbo 128k | **x 20** | **x 60** |
| GPT-5 Pro | **x 30** | **x 240** |
| GPT-5.2 Pro | **x 42** | **x 336** |
| GPT-5.5 Pro | **x 60** | **x 360** |
| GPT-5.4 Pro | **x 60** | **x 360** |
| GPT-4 | **x 60** | **x 120** |

### **Perplexity**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Sonar | **x 2** | **x 2** |
| Sonar Pro | **x 6** | **x 30** |

### **xAI**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| Grok 4.1 Fast | **x 0.4** | **x 1** |
| Grok 4 Fast | **x 0.4** | **x 1** |
| Grok 3 Mini | **x 0.6** | **x 1** |
| Grok 4.3 | **x 2.5** | **x 5** |
| Grok 4.20 | **x 2.5** | **x 5** |
| Grok 4.5 | **x 4** | **x 12** |
| Grok 3 | **x 6** | **x 30** |
| Grok 4 | **x 6** | **x 30** |

### **Z.ai**

| Name | Input modifier | Output modifier |
| --- | --- | --- |
| GLM 4.6 | **x 0.7** | **x 3** |
| GLM 4.7 | **x 0.8** | **x 3** |
| GLM 5.2 | **x 1.08** | **x 3.52** |
| GLM 4.5 | **x 1.2** | **x 4.4** |
| GLM 5.1 | **x 1.96** | **x 6.16** |