Create an API key

Command R7B (12-2024) API: toman pricing and code

cohere/command-r7b-12-2024

JSON output
Create a keyTry it
Input · per 1M tokens
12,983 toman
Output · per 1M tokens
51,933 toman
One 1,000-word request ≈
84 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

Command R7B (12-2024) example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="cohere/command-r7b-12-2024",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const resp = await client.chat.completions.create({
  model: "cohere/command-r7b-12-2024",
  messages: [{ role: "user", content: "Ticket: "For two days I cannot download my invoice and I was charged twice."" }],
  response_format: {
    type: "json_schema",
    json_schema: {
      name: "ticket",
      strict: true,
      schema: {
        type: "object",
        properties: {
          category: { type: "string", enum: ["fani", "mali", "forush"] },
          priority: { type: "integer", minimum: 1, maximum: 5 },
          summary: { type: "string" },
        },
        required: ["category", "priority", "summary"],
        additionalProperties: false,
      },
    },
  },
});
console.log(JSON.parse(resp.choices[0].message.content));
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/command-r7b-12-2024",
    "messages": [{"role": "user", "content": "Classify the ticket and give it a priority from 1 to 5."}],
    "response_format": {"type": "json_object"}
  }'

What is Command R7B (12-2024) good for?

The id for Command R7B (12-2024) in our API is "cohere/command-r7b-12-2024", served from Cohere. Context is 128,000 tokens; past that you have to summarise the history yourself. A single response can run to 4,000 tokens. On price it sits in the "very cheap" band — cheaper than 367 and dearer than 25 of the other paid models in the catalogue.

Capabilities available on this id: it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

For a back-of-envelope figure: about 84 toman per 1,000-word exchange (12,983 in, 51,933 out, per 1M tokens). You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is Schematron V2 Turbo, and Command R7B (12-2024) costs about the same, and its context window is the same size. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 1,190 thousand-word requests on Command R7B (12-2024), and every 1,000 toman is about 11,905 words of round trip. A job with one million input tokens and one million output tokens comes to 64,916 toman in total. Filling this model's 128,000-token window costs 1,662 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "cohere/command-a", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 67× cheaper (84 against 5,626 toman). The context windows differ too: 128,000 against 256,000 tokens. Maximum answer length differs as well: 4,000 against 8,192 tokens.

Cohere has 6 models in our catalogue; the cheapest is Command R7B (12-2024) at 84 toman per thousand words and the dearest Command R+ (08-2024) at 5,626. Among the less common parameters it accepts presence_penalty, top_k — all through the standard request body. It does not support include_reasoning, reasoning, tool_choice, tools, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Nova Micro 1.0 at 128,000 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, extracting data against a fixed schema.

Provider's own description

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out40 toman
Summarising a ten-page document4,000 in + 600 out83 toman
Classifying a thousand short rows120,000 in + 20,000 out2,597 toman

Frequently asked

How do I call Command R7B (12-2024) from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "cohere/command-r7b-12-2024". Nothing else in your code changes.
What does Command R7B (12-2024) cost in toman?
12,983 toman per 1M input tokens and 51,933 toman per 1M output tokens; a 1,000-word request is around 84 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Command R7B (12-2024) take?
Up to 128,000 tokens per request, roughly 96k words. A single answer can reach 4,000 tokens.
Can I stream Command R7B (12-2024)'s output?
Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.