Provider: Cohere
Call Cohere models through Respan Gateway with unified logs, cost, and latency.
Use Respan Gateway to call Cohere models (command-a-reasoning-08-2025, command-a-vision-07-2025, command-a-03-2025, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.
Cohere requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.
Paste this into your coding agent:
Help me set up the Respan gateway to call Cohere models.
Follow https://www.respan.ai/docs/integrations/gateway/model-providers/cohere.mdQuick setup
Get a Respan API key
Sign up and create a key on the API keys page .
Add your Cohere credentials
Configure your Cohere credentials on the Providers page before using the examples below. See Use your own Cohere key.
Send your first request
After configuring your Cohere credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.
Use the OpenAI-compatible Gateway endpoint with the Cohere model ID from the catalog.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_RESPAN_API_KEY",
base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
model="cohere/command-a-reasoning-08-2025",
messages=[{"role": "user", "content": "Hello, Cohere!"}],
)
print(response.choices[0].message.content)More integrations
Cohere models work with every Respan gateway integration:
Switch models
Change the model parameter to call any supported model through the same client. Use the cohere/ prefix to disambiguate when routing across providers. Browse the full list on the Models page .
client.chat.completions.create(model="cohere/command-a-reasoning-08-2025", messages=messages)
client.chat.completions.create(model="cohere/command-a-vision-07-2025", messages=messages)
client.chat.completions.create(model="cohere/command-a-03-2025", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)Use your own Cohere key (BYOK)
Cohere credentials are required. Configure them in Respan or pass them with each request using one of the options below.
Open Providers
Go to the Providers page .
Add Cohere
Select Cohere and paste your cohere.api_key.
Load balancing (Optional)
Add multiple credential sets and use Load balancing weight to distribute traffic across them.
Override credentials per model (Optional)
Use credential_override when one model on a request should use a different Cohere key than the default.
{
"customer_credentials": {
"cohere": { "api_key": "YOUR_COHERE_API_KEY" }
},
"credential_override": {
"cohere/command-a-reasoning-08-2025": { "api_key": "ANOTHER_COHERE_API_KEY" }
}
}Log without proxying (Optional)
Already calling Cohere directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.
import requests
requests.post(
"https://api.respan.ai/api/request-logs/create/",
headers={
"Authorization": "Bearer YOUR_RESPAN_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "cohere/command-a-reasoning-08-2025",
"prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
"completion_message": {"role": "assistant", "content": "Hello from Cohere through Respan."},
"cost": 0.001,
"generation_time": 1.2,
"customer_params": {"customer_identifier": "user_123"},
},
)See the logging guide for the full setup.