Command A+
Command A+ is Cohere's flagship model for enterprise agentic workflows. Cohere Enterprise Agentic Flagship, with a 192K token context window.
/v1/ai/chatOverview
Command A+ is Cohere's flagship model for enterprise agentic workflows. Cohere Enterprise Agentic Flagship, with a 192K token context window.
| Property | Value |
|---|---|
| Model ID | cohere/command-a-plus |
| Context Window | 192,000 tokens |
| Max Output | 64,000 tokens |
| Input Price | $0.44 / 1M tokens |
| Output Price | $2.22 / 1M tokens |
Usage
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'cohere/command-a-plus',
messages: [{ role: 'user', content: 'Using the provided tools, look up the order status for order 4821 and draft a reply to the customer.' }],
}),
});
const { data } = await res.json();
console.log(data.message.content);curl -X POST https://api.yepapi.com/v1/ai/chat \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "cohere/command-a-plus", "messages": [{"role": "user", "content": "Using the provided tools, look up the order status for order 4821 and draft a reply to the customer."}]}'Request Body
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
model | string | Yes | Model ID (e.g. cohere/command-a-plus) | — |
messages | Message[] | Yes | Array of { role, content } objects | — |
maxTokens | number | No | Maximum tokens in the response | Model default |
temperature | number | No | Sampling temperature (0.0–2.0) | 1.0 |
topP | number | No | Nucleus sampling threshold | 1.0 |
frequencyPenalty | number | No | Penalize repeated tokens | 0 |
presencePenalty | number | No | Penalize tokens already present | 0 |
stream | boolean | No | Enable SSE streaming | false |
All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.
Response
{
"ok": true,
"data": {
"model": "cohere/command-a-plus",
"message": {
"role": "assistant",
"content": "Order 4821 shipped on the 24th and is out for delivery today. Draft: \"Good news \u2014 your order is out for delivery today. Here is the tracking link; reply here if it has not arrived by 6pm.\""
},
"usage": {
"promptTokens": 16,
"completionTokens": 245,
"totalTokens": 261
}
}
}Streaming
Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:
data: {"delta":{"content":"Use"},"model":"cohere/command-a-plus","index":0}
data: [DONE]We handle auth, billing, and response normalization — you just send messages.
Fugu Ultra v2
Sakana AI's higher-performance Fugu model — a learned multi-agent orchestration system routing across stronger specialists, with a 1M token context window and 128K output tokens.
Ember-1
Ember-1 is a specialised reasoning model from Fireworks Research, built on Moonshot's Kimi K3. Fireworks Efficient Reasoning on Kimi K3, with a 1M token context window.