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 0.5x 2.5
Claude Haiku 3.5 x 1.6x 8
Claude Haiku 4.5 x 2x 10
Claude Sonnet 3.7 x 6x 30
Claude Sonnet 4 x 6x 30
Claude Sonnet 4.5 x 6x 30
Claude Sonnet 4.6 x 6x 30
Claude Opus 4.5 x 10x 50
Claude Sonnet 3.5 x 12x 60
Claude Opus 4 x 30x 150
Claude Opus 4.1 x 30x 150

Cohere

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

DeepSeek

Name
Input modifier
Output modifier
DeepSeek V3 x 0.6x 2.4
DeepSeek R1 x 1.4x 4.8

Google

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

Meta

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

Mistral

Name
Input modifier
Output modifier
Mistral - Open Mistral 7b x 0.06x 0.11
Mistral - Mistral Small x 0.06x 0.22
Mistral - Open Mixtral 8x7b x 1.08x 1.08
Mistral - Open Mixtral 8x22b x 4x 12
Mistral - Mistral Large x 4x 12

MoonshotAI

Name
Input modifier
Output modifier
Kimi K2 x 1x 4.8

OpenAI

Name
Input modifier
Output modifier
GPT-5 Nano x 0.1x 0.8
GPT-4.1 Nano x 0.2x 0.8
GPT-4o Mini ourdefaultx 0.3x 1.2
GPT-5 Mini x 0.5x 4
GPT-4.1 Mini x 0.8x 3.2
GPT-3.5 Turbo x 1x 3
GPT-5.1 x 2.5x 20
GPT-5.1 Chat x 2.5x 20
GPT-5 x 2.5x 20
GPT-5.2 x 3.5x 28
GPT-4.1 x 4x 16
GPT-4o x 5x 20
GPT-4 Turbo 128k x 20x 60
GPT-5.2 Pro x 42x 336
GPT-4 x 60x 120

Perplexity

Name
Input modifier
Output modifier
Sonar x 2x 2
Sonar Pro x 6x 30

xAI

Name
Input modifier
Output modifier
Grok 4 Fast x 0.4x 1
Grok 4.1 Fast x 0.4x 1
Grok 3 Mini x 0.6x 1
Grok 3 x 6x 30
Grok 4 x 6x 30

Z.ai

Name
Input modifier
Output modifier
GLM 4.6 x 0.7x 3
GLM 4.5 x 0.7x 3.1
GLM 4.7 x 0.8x 3