Home/Models/Command R
MODEL DOSSIER / ENGLISH

Command R

command-r-08-2024

科希尔text2024-08-30

Command R is a text model from 科希尔. The snapshot records a release date of 2024-08-30. Context window: 128K tokens. Maximum output: 4K tokens. Input: text. Output: text. Capabilities recorded: tool calls, open weights.

Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页

Context128K
Max output4K
Inputtext
Outputtext
Official input¥1 / 1M
Official output¥4.01 / 1M
Capabilitiestool calls, open weights
Release2024-08-30

Official list price

CNY / 1M TOKENS

Official list price in the directory snapshot: ¥1 input and ¥4.01 output per 1M tokens, in CNY. Relay prices below are what individual sites listed; they can be lower or higher, and they are not official prices.

Relay coverage

2 SITES

2 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥1–¥1.0143 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.

SiteDomainRelay price / 1MVerification
OmniaKeyomniakey.com¥1enterprise
XycAi(星道智能)xycai.us¥1.0143enterprise

How to verify this model on a relay

THREE STEPS
  1. Send a short request to the relay and read the model field in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution.
  2. Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
  3. Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.

Same publisher

科希尔

Questions

FAQ

What is the context window of Command R?

The snapshot records 128,000 tokens.

How much does Command R cost?

Official list price: ¥1 input / ¥4.01 output per 1M tokens in CNY, per the directory snapshot. 2 relay sites listed it at ¥1–¥1.0143 per 1M input tokens.

Is a relay really serving Command R?

A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.

Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.