Command A pricing and routing profile
Command A from Cohere lists at $2.50 per million input tokens and $10.00 per million output tokens, with a 256,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Structured output
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $1.60 |
| Chat reply (2,000 in, 400 out) | $9.00 |
| Retrieval-augmented answer (8,000 in, 500 out) | $25.00 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for Command A. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Who serves Command A
| Host | Input / output per 1M | Log probabilities | Uptime, last 30 min |
|---|---|---|---|
| Cohere | $2.50 / $10.00 | no | — |
A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.
Cheaper models that can answer first
Models priced below Command A that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Qwen3.8 Max (0902) | $2.00 / $6.00 | 29% |
| Qwen3.8 2.4T A95B | $2.00 / $6.00 | 29% |
| Grok 4.6 | $2.00 / $6.00 | 29% |
| Grok 4.5 | $2.00 / $6.00 | 29% |
| Grok 4.7 | $1.60 / $4.80 | 43% |
| Qwen3.7 Max | $1.48 / $4.42 | 48% |
Compare Command A
- Command A vs Claude Opus 5.5
- Command A vs Claude Sonnet 5
- Command A vs Claude Fable 5.1
- Command A vs Claude Opus 5
- Command A vs GPT-6 Sol
- Command A vs GPT-6 Astra
- Command A vs GPT-5.6 Sol
- Command A vs GPT-5.6 Terra
- Command A vs GPT-5.5
- Command A vs GPT-5.4
- Command A vs Gemini 3.1 Pro Preview
- Command A vs Gemini 3.8 Flash
- Command A vs Grok 4.7
- Command A vs Qwen3.8 Max (0902)
- Command A vs Kimi K3
- Command A vs GLM 5.3
- Command A vs DeepSeek V4 Pro 0423
- Command A vs Mistral Large 3 2512
- Command A vs Nova Premier 1.0
- Command A vs GPT-6 Luna
- Command A vs GPT-5.6 Luna
- Command A vs GPT-5.4 Mini
- Command A vs GPT-5.4 Nano
- Command A vs GPT-4.1 Mini
- Command A vs gpt-oss-120b
- Command A vs gpt-oss-20b
- Command A vs Claude Haiku 4.5
- Command A vs Gemini 3.5 Flash Lite
- Command A vs Gemma 4 31B
- Command A vs DeepSeek V4.1 Flash
- Command A vs DeepSeek V4 Flash 0731
- Command A vs GLM 5.3 Flash
- Command A vs Hy4 preview
- Command A vs MiMo-V2.6-Flash
- Command A vs Nemotron 3.5 Lightning
- Command A vs Nemotron 3 Ultra
- Command A vs Qwen3.8 Flash
- Command A vs Qwen3.7 Flash
- Command A vs Qwen3.8 27B
- Command A vs MiniMax M3
- Command A vs Kimi K2.6
- Command A vs Mistral Small 4
- Command A vs Ministral 3 8B 2512
- Command A vs Llama 4 Maverick
- Command A vs Llama 3.3 70B Instruct
- Command A vs Nova Lite 1.0
- Command A vs Nova Micro 1.0
- Command A vs Command R7B (12-2024)
- Command A vs Phi 4
Questions
How much does Command A cost?
Command A lists at $2.50 per million input tokens and $10.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $9.00 per 1,000 requests.
What is the context window of Command A?
256,000 tokens.
Can a cheaper model replace Command A?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Command A on one half of your requests and make at most three answers worse on the other.