Skip to content
Rapid Router
All models
Together AI

Together AI API pricing in India

7 Together AI models live through one API key and one balance, priced per million tokens in rupees.

Models live
7
Lowest input
₹4.16/M
Max context
1M

Every Together AI model below is callable right now through Rapid Router with one API key. The price next to each model is the provider's list price per million tokens, shown in rupees at today's billing rate (the market rate plus our currency margin); in dollars it is exactly what your balance is debited. Our platform fee is charged once, when you buy credits, so there is nothing added per request.

To use a Together AI model, point the OpenAI SDK (or any OpenAI-compatible client) at https://rapidrouter.ai/api/v1, set the model string to the id shown in grey, and send the same request you send today. Top up with UPI or a card and a GST invoice follows every recharge.

To weigh a Together AI model against Claude, GPT, Gemini or any other family, the model rankings put independent LMArena ratings next to each price, and the cost calculator works out what your own monthly token volume would cost on every model.

DeepSeek V4.1 FlashVisionReasoningTools

DeepSeek V4.1 Flash model for reasoning and agentic coding

₹29.72 in · ₹119 out /1M

together/deepseek-ai/deepseek-v4.1-flash, by Together AI1mo ago1M context
DeepSeek V4.1 Flash 1017VisionReasoningTools

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

₹29.72 in · ₹119 out /1M

together/deepseek-ai/deepseek-v4.1-flash-1017, by Together AI13d ago1M context
Muse Spark OpenVisionReasoningTools

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

₹124 in · ₹421 out /1M

together/meta-models/muse-spark-open-816b-a42b, by Together AI15d ago1M context
MiniMax-M3.1-FlashVisionReasoningTools

Frontier multimodal coding model with 1M context window and tunable thinking depth

₹14.86 in · ₹59.45 out /1M

together/minimaxai/minimax-m3.1-flash, by Together AI11d ago1M context
Nemotron 3.5 Super VL 120B A12BVisionReasoningTools

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

₹14.86 in · ₹49.54 out /1M

together/nvidia/nvidia-nemotron-3.5-super-vl, by Together AI15d ago262K context
Beam 1.0 501B A23BReasoningTools

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

₹39.63 in · ₹119 out /1M

together/reflection/beam-1.0-501b-a23b, by Together AI25d ago1M context
Tev1 4B ExperimentalLowest cost

₹4.16 in · Free out /1M

together/together/tev1-4b-experimental, by Together AI

Together AI API: common questions

How do I get a Together AI API key in India?
Create a Rapid Router account, open API keys in the dashboard and create a key. That one key calls every Together AI model, plus Claude, GPT, Gemini and 600+ others, through the OpenAI SDK with the base URL https://rapidrouter.ai/api/v1. You do not need a separate Together AI account or an international card.
Can I pay for the Together AI API with UPI?
Yes. Top up your Rapid Router balance in rupees with UPI or an Indian card, and every recharge comes with a GST invoice. Together AI requests are then billed from that balance at Together AI's list price per million tokens.
What does the Together AI API cost?
Input prices run from ₹4.16 per million tokens (Tev1 4B Experimental) to ₹124 (Muse Spark Open). Each model's input and output price is in the table on this page.
Is there a free Together AI API?
Not right now: every Together AI model here is billed at its list price. The daily free allowance on Rapid Router covers the models marked Free in the catalogue.
Which Together AI model should I use?
Start with the cheapest model that handles your task and move up only for the requests it gets wrong. For long documents, DeepSeek V4.1 Flash 1017 reads up to 1M tokens in one request. The best model rankings compare Together AI models with every other family on independent votes and price.