Command A+
Command A+ is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.
Use it for
- Teams evaluating rag, agents, and long context
- Workloads that can use a 128k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Command
- Released
- 2026-05-20
- Context
- 128k
- Max output
- 64,000
- Parameters
- 218B total / 25B active
- Architecture
- Mixture of Experts
- Knowledge cutoff
- 2025-04
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Cheapest of 1 route · Cohere API
About
Command A+ is Cohere's open-weight sparse mixture-of-experts model for enterprise agentic, multimodal, multilingual, RAG, and reasoning-heavy workloads. It combines text and image inputs, tool use, structured outputs, 48-language support, and hardware-efficient deployment that can run on one B200 or two H100 GPUs.
Command A+ is a proprietary model in the Command family. The structured metadata tracks a 128k-token context window, multimodal input, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through Cohere API. Headline tracked benchmarks include AIME 2025 90.0, Massive Multi-discipline Multimodal Understanding 75.1, and τ-bench 85.0.
Top use-case fit: coding, agents, and build tasks
RAG
Included by capability and metadata signals in the decision map.
Agents
1 relevant benchmark in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Cohere API | - | - | ServerlessProvisionedPartial |
Available via routers & gateways(4)
LiteLLM
GatewayOpen-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.
OpenRouter
HybridUnified 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.
Portkey
GatewayProduction 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.
Kong AI Gateway
GatewayMulti-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.
Capabilities
Benchmark peer barsfor Agents
Benchmark scores(3)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| AIME 2025 | 90.0 | AIME 2025 (accuracy) | https://cohere.com/blog/command-a-plus |
| Massive Multi-discipline Multimodal Understanding | 75.1 | MMMU (accuracy) | https://cohere.com/blog/command-a-plus |
| τ-bench | 85.0 | τ²-Bench Telecom (accuracy) | https://cohere.com/blog/command-a-plus |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(3)
Compare Command A+ with other models
Comparison and alternatives
Browse all comparisons →Frequently asked questions
What is the context window of Command A+?
Command A+ has a context window of 128k tokens.
What is the max output of Command A+?
Command A+ can generate up to 64,000 output tokens.
When was Command A+ released?
Command A+ was released on 2026-05-20.
Which providers offer Command A+?
Command A+ is available from 1 provider: Cohere API.
What benchmarks has Command A+ been tested on?
Command A+ has been evaluated on 3 benchmarks, including AIME 2025, Massive Multi-discipline Multimodal Understanding, τ-bench.
Cheapest of 1 route · Cohere API