- MODEL STATUS
- USAGE DATA
- LIMITS
- HUMAN
Short answer
How can I check my token counts and available Cohere models?
Your AI uses the Cohere MCP to list active models and calculate the token weight of your text. This helps you stay within context window limits. You'll see exactly what's available and how much space your data takes up.
Audit outcomes
Where your data lands.
The AI organizes your audit results into these categories.
MODEL STATUS
Active model list
The AI pulls a list of models available on your plan. You'll see exactly what you can call.
USAGE DATA
Token weight counts
The AI calculates the token count for any text you provide. This prevents context overflow errors.
LIMITS
Context window checks
The AI compares your text weight against model limits. You'll know if a prompt is too large.
HUMAN
Manual plan updates
The AI cannot change your Cohere subscription or add new models. You must handle billing and plan upgrades yourself.
The workflow
What your AI does when the audit request arrives.
The AI performs the technical checks to give you a clear picture of your usage.
Identify available models
The AI checks your Cohere account to see which specific models you have permission to use.
list_modelsCalculate text weight
The AI processes your input text to determine the exact number of tokens it contains.
tokenize_textVerify context limits
The AI uses the token count to check if your content fits within the model's window.
tokenize_textReport findings
The AI presents the model list and token counts in a readable format for your review.
list_modelstokenize_text
Try it
Copy these to start.
Use these prompts to trigger the audit immediately.
Starting points
These are basic requests. Swap out the text or model names to fit your specific needs.
Cohere Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_K2rlWzCd7or9FAq78qCN7N91Fzl9RZitKXOe4TMF/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Cohere capabilities are ready to use.
{
"mcpServers": {
"cohere-embed-rerank-mcp": {
"url": "https://edge.vinkius.com/vk_preview_K2rlWzCd7or9FAq78qCN7N91Fzl9RZitKXOe4TMF/mcp"
}
}
}List all the Cohere models currently available on my plan.
How many tokens is this specific document using: [paste text here]?
Check if the text from my 'project_brief.txt' file will fit in the rerank model.
Compare the token count of my current prompt against the limits of the available models.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Cohere once, then ask.
Just link your account once. Your credentials stay encrypted, and you can start auditing immediately through your preferred client.
Connect Cohere to your AIFAQ
How this task behaves.
- 01
Can the AI upgrade my Cohere plan?
No. The AI can only read your current model availability. You must manage your subscription through the Cohere dashboard.
- 02
Does the AI change my token usage?
No. The AI only calculates and reports the token counts. It does not perform any actions that consume your API credits.
- 03
Can I use this to check my Embed model limits?
Yes. You can use the tokenization tool to see how much text your Embed models can handle.
- 04
Will the AI automatically switch models if I hit a limit?
No. The AI will report that you have exceeded a limit, but it won't switch models or change your settings for you.
- 05
How accurate are the token counts?
The counts are exact because the AI uses the specific tokenization tool provided by the connector.
More questions about Cohere? The Connector page answers them. See everything the Cohere Connector can do
Connect Cohere to Claude, Cursor, ChatGPT & more
