Cohere models, priced in toman
8 Cohere models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Cohere on uttapen
Cohere currently has 8 models in the uttapen catalogue. 1 of them are free; the rest bill against a toman wallet.
The spread inside Cohere alone is wide: Command R7B (12-2024) runs about 84 toman for a 1,000-word request, while Command R+ (08-2024) costs 5,626 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Cohere output price undercuts about 53% of the other paid models.
On capabilities: 3 take image input, 4 support tool calling, 2 do multi-step reasoning. The longest context belongs to Command A, at 256,000 tokens.
Every Cohere model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which Cohere model should I start with?
- Command R7B (12-2024)84 · per 1,000 wordsThe cheapest way in: about 84 toman for a 1,000-word request.
- North Mini Code (free)0 · per 1,000 wordsThe cheapest Cohere model with tool calling — for agents and for wiring the model to your own API.
- Command A5,626 · per 1,000 wordsThis supplier's longest context, 256,000 tokens — for long documents and RAG.
- Command A+810 · per 1,000 wordsWhen the input is an image or a scanned invoice.
Every Cohere model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Command Acohere/command-a | JSON output | 256,000 | 865,548 | 3,462,194 |
Command A+cohere/command-a-plus | Image inputTool callingReasoningJSON output | 192,000 | 103,866 | 519,329 |
Command R (08-2024)cohere/command-r-08-2024 | Tool callingJSON output | 128,000 | 51,933 | 207,732 |
Command R+ (08-2024)cohere/command-r-plus-08-2024 | Tool callingJSON output | 128,000 | 865,548 | 3,462,194 |
Command R7B (12-2024)cohere/command-r7b-12-2024 | JSON output | 128,000 | 12,983 | 51,933 |
North Mini Codecohere/north-mini-code:free | Free · shared capacityTool callingReasoning | 256,000 | 0 | 0 |
Embed 5 Fastcohere/embed-5-fast | Image inputEmbeddings | 128,000 | 27,698 | — |
Embed 5 Procohere/embed-5-pro | Image inputEmbeddings | 128,000 | 41,546 | — |
Common questions about the Cohere API
- How do I reach the Cohere API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the Cohere model id. No international card, no VPN. - What do Cohere models cost in toman?
- It depends on the model: the cheapest, Command R7B (12-2024), is about 84 toman for a 1,000-word request, and the dearest, Command R+ (08-2024), about 5,626 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Cohere models are on uttapen?
- 8, 1 of them free. 4 support tool calling and 3 accept image input. 2 are embedding models for /v1/
embeddings. The catalogue re-syncs hourly, so a newly released model shows up here on its own. - What are the limits on the free Cohere models?
- They have a daily per-user cap and share their capacity with everyone else. When that shared pool runs out the request is refused with a clear error and your wallet is left alone.