Command

Name: Command
Author: Cohere

Released

2023-11-14

Last refreshed

2026-06-15

Status

Researched 126d ago

DeprecatedOpen weightsCommercial use: non-commercialClassificationJSON / Tool use

Command is a legacy integration reference; keep it only while you identify a current replacement.

Cohere releases · 5 in the last 12 monthsChangelog →

Specifications

Family: Command
Released: 2023-11-14
Context: 4k
Max output: 4,096
Architecture: Decoder Only
Knowledge cutoff: 2023-02
Specialization: general
Openness: Open weights
License: CC-BY-NC-4.0Commercial use: non-commercial
Weights: Unknown
Code: Unknown
Training: Fine-tuned

Created by

Cohere

Empowering developers with advanced language AI.

Toronto, Ontario, Canada

Founded 2022

Website

Pricing

Output / 1M

$2.00

Input / 1M

$1.00

Cheapest of 4 routes · Cohere API

Providers(4)

AWS Bedrock OCI Generative AI Cohere API Scale AI GenAI Platform

View 4 provider routes

About

Command is Cohere's legacy instruction-following conversational model. Cohere lists it as deprecated as of September 15, 2025; use current Command A or Command R variants for new builds.

Provider price ladder

Compare all 4

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
Cohere API	$1.00	$2.00	Serverless
AWS Bedrock	$1.50	$2.00	Serverless
OCI Generative AI	-	-	ServerlessPartial
Scale AI GenAI Platform	-	-	ServerlessPartial

Available via routers & gateways(5)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSCohere API

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughCohere API

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionCohere API

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Kong AI Gateway

Gateway

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

SubscriptionCohere API