Command Nightly
command-nightlyPricing
List prices at Cohere, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.00 | $2.00 |
What it costs a month
At Cohere list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$450
- RAG over documents2,000 requests a day, 8K in / 0.6K out$552
- Coding agent1,000 requests a day, 40K in / 2K out$1,320
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,880
Where to run it
1 host serve Command Nightly. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
CohereLab API command-nightly | $1.00 / $2.00 | command-nightly |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Cohere.
Smaller Cohere models
- 40% less
Other frontier labs
- 32% less
- 63% less
- 84% less
- 84% less
Open-weight picks
- 30% less
- 31% less
- 35% less
- 37% less
Call it
Using Cohere's API.
from litellm import completion
response = completion(
model="cohere/command-nightly",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Command Nightly cost?
On Cohere, Command Nightly costs $1.00 per million input tokens and $2.00 per million output tokens.
Which APIs offer Command Nightly?
Command Nightly runs on 1 API: Cohere.
What is Command Nightly's context window?
4K tokens, with up to 4K tokens in one reply.
Is Command Nightly being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Command Nightly?
Models that cost less and keep most of what it can do: C4ai Aya Expanse 32B on Cohere Chat (40% less), Gemini 3.5 Flash Lite on Google AI Studio (32% less), GPT-5.4 Nano on OpenAI (63% less) and Motif 3 on ai& (30% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Command Nightly's API model id?
Use command-nightly with Cohere.
Sources
Raw catalog entry for command-nightly on Cohere
{
"input_cost_per_token": 0.000001,
"litellm_provider": "cohere",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "completion",
"output_cost_per_token": 0.000002
}