Cohere

Use Cohere with Blazen — construct the CohereProvider and call complete().

Cohere is an OpenAI-compatible LLM provider. Construct it like any other Blazen provider — build a list of ChatMessages, call complete() (or stream()), and read back a typed ModelResponse.

At a glance

Provider id	cohere
Base URL	https://api.cohere.ai/compatibility/v1
Default model	command-a-08-2025
API key env var	COHERE_API_KEY
Auth	Authorization: Bearer <key>

Set COHERE_API_KEY in the environment and Blazen reads it automatically, or pass the key explicitly when you construct the provider.

Capabilities

Capability	Supported
Streaming	Yes
Tool calling	Yes
Structured output	Yes
Vision	No
Model listing	No
Embeddings	Yes

Usage

Construct the provider and call complete(). The default model is command-a-08-2025; override it with with_model / model when you need a different one.

use blazen_llm::{Model, ModelRequest, ChatMessage};
use blazen_provider_cohere::CohereProvider;

// Reads COHERE_API_KEY from the environment, or pass the key to `new`.
let model = CohereProvider::new(std::env::var("COHERE_API_KEY")?);

let resp = model
    .complete(ModelRequest::new(vec![ChatMessage::user("Hello")]))
    .await?;
println!("{}", resp.content.unwrap_or_default());

from blazen import CohereProvider, ProviderOptions, ChatMessage

# Omit the api_key to read COHERE_API_KEY from the environment.
model = CohereProvider(options=ProviderOptions(api_key="..."))

resp = await model.complete([ChatMessage.user("Hello")])
print(resp.content)

import { CohereProvider, ChatMessage } from "blazen";

// Omit apiKey to read COHERE_API_KEY from the environment.
const model = CohereProvider.create({ apiKey: "..." });

const resp = await model.complete([ChatMessage.user("Hello")]);
console.log(resp.content);

Streaming

async for chunk in model.stream([ChatMessage.user("Count to five")]):
    print(chunk.delta, end="")

await model.stream([ChatMessage.user("Count to five")], (chunk) => {
  if (chunk.delta) process.stdout.write(chunk.delta);
});

See also

• Models & Providers — the canonical provider + ModelManager guide