Free Trial, Pro and Team pricing

Start free. Add a plan when you need more.

Every plan includes Qwen3.8-27B, the model we host ourselves in India. Pro and Team add a monthly credit you can spend on any other model. All prices are before GST.

Try the API

Free Trial

₹0 for 15 days

Qwen3.8-27B at no charge. No card needed.

Qwen3.8-27B: Unlimited
Credit for other models: Prepaid wallet
Requests at once: 1
Requests per minute: 20
API keys: 1

Unlimited applies to Qwen3.8-27B, which we host ourselves. It runs within your plan's request limits; when those are reached, further requests wait their turn.

Get your API key →

Recommended

Pro

₹2,499/month + GST

Unlimited Qwen3.8-27B, plus ₹2,000 credit a month for every other model.

Qwen3.8-27B: Unlimited
Credit for other models: ₹2,000/month
Requests at once: 2
Requests per minute: 60
API keys: 1

Unlimited applies to Qwen3.8-27B, which we host ourselves. It runs within your plan's request limits; when those are reached, further requests wait their turn.

Get Pro →

For teams and agencies

Team

₹9,999/month + GST

Unlimited Qwen3.8-27B, plus ₹8,000 credit a month for every other model.

Qwen3.8-27B: Unlimited
Credit for other models: ₹8,000/month
Requests at once: 8
Requests per minute: 200
API keys: Up to 10

Unlimited applies to Qwen3.8-27B, which we host ourselves. It runs within your plan's request limits; when those are reached, further requests wait their turn.

Get Team →

Other models, metered against your credit or wallet: DeepSeek V4.1 Flash, DeepSeek V4.1 Flash 1M, GLM-5.3 Flash, GLM-5.3, Gemma 4 31B IT, Gemma 4 26B A4B IT, Qwen3-Coder-Next, gpt-oss-120b, Nemotron 3.5 Super VL 120B A12B, Perplexity Decider v1.1 (27B), and the other models in the price table below.

Not sure which model fits which task? Book a free cost check →

Prices before 18% GST.

Other ways to buy

Pay as you go

From ₹7.40 / ₹24.67

Per 1M input / output tokens on GLM-5.3 Flash, plus GST. Rates vary by model. Pay from prepaid rupee credit.

Get your API key →

Compare per-model token prices.

Prices as of 13 Nov 2026. Rupees per 1M tokens, before 18% GST. Each model shows where it is processed and who hosts it. Use the model ID in your API calls. Apart from Qwen3.8-27B, models are metered against your plan credit or prepaid wallet.

Processed in India

Your prompts and responses stay in India.

Model	Input / 1M	Output / 1M
DeepSeek V4.1 Flash`deepseek-v4.1-flash`India (Noida) · IndieRouter	₹8.25	₹57.20
DeepSeek V4.1 Flash 1M`deepseek-v4.1-flash-1m`India (Noida) · IndieRouter	₹16.50	₹66
Nemotron 3.5 Super VL 120B A12B`nemotron-3.5-super-vl-120b-a12b`India (Noida) · IndieRouter	₹18.77	₹62.56
Perplexity Decider v1.1 (27B)`pplx-decider-v1.1`India (Noida) · IndieRouter	₹8.80	Input-only billing
`qwen3.8-27b-fp8`India (Noida) · IndieRouter	₹37.53	₹293.97
Qwen3.8-27B`qwen38-27b`India · IndicStackUnlimited on Free Trial, Pro and Team	₹21	₹190

Processed in India or outside India

The first route listed answers. If it is unavailable, the other route answers and the call is billed at that route's rate.

Model	Input / 1M	Output / 1M
Gemma 4 26B A4B IT`gemma-4-26b-a4b-it`First: Outside India · Novita AIFallback: India (Noida) · IndieRouter	₹13.43Fallback ₹13.75	₹41.33Fallback ₹46.28
Gemma 4 31B IT`gemma-4-31b-it`First: Outside India · Novita AIFallback: India (Noida) · IndieRouter	₹14.47Fallback ₹17.51	₹41.33Fallback ₹50.04
GLM-5.3`glm-5.3`First: Outside India · Novita AI, Alibaba Cloud, Z.ai, Together AI, ComputeBase, Melious, CanopyWave, AWS BedrockFallback: India (Noida) · IndieRouter	₹144.65Fallback ₹151.36	₹454.62Fallback ₹482.87
GLM-5.3 Flash`glm-5.3-flash`First: India (Noida) · IndieRouterFallback: Outside India · CanopyWave, ComputeBase, Melious	₹7.40Fallback ₹15.50	₹24.67Fallback ₹51.66

Processed outside India

Answered by the hosts named under each model, outside India. Use a model processed in India if your data must stay in India.

Model	Input / 1M	Output / 1M
`abliterated-model`Outside India · Abliteration	₹103.32	₹309.97
`abliterated-model-large-flash`Outside India · Abliteration	₹103.32	₹206.65
`abliterated-model-large-v2`Outside India · Abliteration	₹309.97	₹516.62
`codestral-2508`Outside India · Mistral AI	₹31	₹92.99
`deepseek-v4-flash`Outside India · Microsoft Azure	₹19.63	₹52.69
`deepseek-v4-flash-0731`Outside India · Alibaba Cloud, Novita AI, CanopyWave	₹45.46	₹136.39
`deepseek-v4-pro`Outside India · Microsoft Azure, DeepSeek, Novita AI	₹179.78	₹359.56
`deepseek-v4.1-flash-1017`Outside India · Alibaba Cloud, Together AI, Novita AI, Melious, DeepSeek, Boundless	₹31	₹123.99
`deepseek/deepseek-v4.1-flash`Outside India · Novita AI, Melious, Alibaba Cloud, DeepSeek, Boundless, Together AI	₹31	₹123.99
`devstral-2512`Outside India · Mistral AI	₹41.33	₹206.65
`glm-4-32b-0414-128k`Outside India · Z.ai	₹10.33	₹10.33
`glm-4.5`Outside India · EmberCloud, Z.ai	₹61.99	₹227.31
`glm-4.5-air`Outside India · EmberCloud, Z.ai	₹13.43	₹87.82
`glm-4.5-airx`Outside India · Z.ai	₹113.66	₹464.95
`glm-4.5-x`Outside India · Z.ai	₹227.31	₹919.57
`glm-4.5v`Outside India · Novita AI, Z.ai	₹61.99	₹185.98
`glm-4.6`Outside India · Novita AI, Z.ai	₹56.83	₹227.31
`glm-4.6v`Outside India · Novita AI, Z.ai	₹31	₹92.99
`glm-4.6v-flashx`Outside India · Z.ai	₹4.13	₹41.33
`glm-4.7`Outside India · EmberCloud, Novita AI, Z.ai	₹39.26	₹204.58
`glm-4.7-flashx`Outside India · Z.ai	₹7.23	₹41.33
`glm-5`Outside India · EmberCloud, Novita AI, Z.ai	₹61.99	₹227.31
`glm-5-turbo`Outside India · Z.ai	₹123.99	₹413.29
`glm-5.1`Outside India · Z.ai	₹144.65	₹454.62
`glm-5v-turbo`Outside India · Z.ai	₹123.99	₹413.29
gpt-oss-120b`gpt-oss-120b`Outside India · AWS Bedrock, Cerebras, Together AI	₹15.50	₹61.99
`gpt-oss-20b`Outside India · AWS Bedrock, Groq	₹7.23	₹31
`kimi-k2.5`Outside India · EmberCloud	₹36.81	₹204.58
`kimi-k2.6`Outside India · Microsoft Azure, CanopyWave, Moonshot AI, Novita AI	₹98.16	₹413.29
`kimi-k2.7-code`Outside India · Novita AI, CanopyWave, Alibaba Cloud	₹98.16	₹413.29
`kimi-k2.7-code-highspeed`Outside India · CanopyWave	₹196.31	₹826.58
`kimi-k3`Outside India · Moonshot AI, CanopyWave, Novita AI, Together AI, Nebius, Alibaba Cloud, Melious	₹309.97	₹1,549.85
`kimi-k3.1-pro`Outside India · Moonshot AI, Nebius, Together AI, Microsoft Azure, CanopyWave	₹206.65	₹1,033.23
`kimi-k3.1-pro-highspeed`Outside India · Moonshot AI	₹413.29	₹2,066.46
`llama-3.1-70b-instruct`Outside India · AWS Bedrock	₹74.39	₹74.39
`llama-3.1-8b-instruct`Outside India · AWS Bedrock, Novita AI	₹22.73	₹22.73
`llama-3.3-70b-instruct`Outside India · Novita AI	₹13.95	₹41.33
`llama-4-maverick-17b-instruct`Outside India · AWS Bedrock, Novita AI	₹24.80	₹100.22
`llama-4-scout-17b-instruct`Outside India · AWS Bedrock, Novita AI	₹17.56	₹68.19
`mimo-v2.6-flash`Outside India · Xiaomi, Boundless, CanopyWave	₹14.47	₹28.93
`mimo-v2.6-pro`Outside India · Xiaomi, Boundless	₹44.95	₹89.89
`mimo-v2.6-pro-ultraspeed`Outside India · Xiaomi	₹449.46	₹898.91
`minimax-m2`Outside India · MiniMax	₹20.66	₹103.32
`minimax-m2.1`Outside India · MiniMax, Novita AI	₹27.90	₹113.66
`minimax-m2.1-lightning`Outside India · MiniMax	₹12.40	₹49.60
`minimax-m2.5`Outside India · AWS Bedrock, EmberCloud, Novita AI	₹31	₹123.99
`minimax-m2.5-highspeed`Outside India · Novita AI	₹61.99	₹247.98
`minimax-m2.7`Outside India · Novita AI	₹31	₹123.99
`minimax-m3`Outside India · MiniMax, Novita AI, CanopyWave, Nebius	₹61.99	₹247.98
`MiniMax-M3.1-Flash`Outside India · MiniMax, Together AI, Novita AI, Boundless	₹15.50	₹61.99
`minimax-text-01`Outside India · MiniMax	₹20.66	₹113.66
`ministral-14b-2512`Outside India · Mistral AI	₹20.66	₹20.66
`ministral-3b-2512`Outside India · Mistral AI	₹10.33	₹10.33
`ministral-8b-2512`Outside India · Mistral AI	₹15.50	₹15.50
`mistral-embed`Outside India · Mistral AI	₹10.33	Input only
`mistral-large-2512`Outside India · Mistral AI	₹51.66	₹154.98
`mistral-large-4`Outside India · Mistral AI	₹72.33	₹216.98
`mistral-large-latest`Outside India · Mistral AI	₹413.29	₹1,239.88
`mistral-small-2506`Outside India · Mistral AI	₹10.33	₹31
`muse-wonder-1.0`Outside India · Meta	₹413.29	₹2,066.46
`qwen-flash`Outside India · Alibaba Cloud	₹5.17	₹41.33
`qwen-max`Outside India · Alibaba Cloud	₹165.32	₹661.27
`qwen-plus`Outside India · Alibaba Cloud	₹41.33	₹123.99
`qwen-plus-latest`Outside India · Alibaba Cloud	₹41.33	₹123.99
`qwen/qwen3.8-27b`Outside India · Alibaba Cloud	₹51.66	₹309.97
`qwen/qwen3.8-flash`Outside India	₹11.68	₹39.47
`qwen/qwen3.8-max-0902`Outside India	₹170.48	₹511.55
`qwen/qwen3.8-omni-flash`Outside India	₹44.43	₹171.52
`qwen3-235b-a22b-fp8`Outside India · Novita AI	₹20.66	₹82.66
`qwen3-235b-a22b-instruct-2507`Outside India · Nebius, Novita AI	₹20.66	₹61.99
`qwen3-30b-a3b-instruct-2507`Outside India · Nebius	₹10.33	₹31
`qwen3-coder-30b-a3b-instruct`Outside India · Novita AI	₹7.23	₹27.90
`qwen3-coder-flash`Outside India · Alibaba Cloud	₹31	₹154.98
Qwen3-Coder-Next`qwen3-coder-next`Outside India · AWS Bedrock, EmberCloud	₹11.16	₹69.74
`qwen3-max`Outside India · Alibaba Cloud, Novita AI	₹309.97	₹1,549.85
`qwen3-vl-30b-a3b-instruct`Outside India · Novita AI	₹20.66	₹72.33
`qwen3-vl-plus`Outside India · Alibaba Cloud	₹20.66	₹165.32
`qwen3.5-9b`Outside India · Together AI	₹10.33	₹15.50
`qwen3.6-plus`Outside India · Alibaba Cloud	₹51.66	₹309.97
`qwen3.7-max`Outside India · Alibaba Cloud	₹51.66	₹309.97
`qwen3.7-plus`Outside India · Alibaba Cloud	₹51.66	₹309.97
`qwen3.8-flash-next`Outside India · CanopyWave	₹20.77	₹51.66
`qwen3.8-max`Outside India · Novita AI, Alibaba Cloud	₹206.65	₹619.94
`zai-glm-5.2`Outside India · Nebius, Novita AI, Z.ai, CanopyWave	₹144.65	₹454.62

What would your token workload cost?

Estimate your token bill

Pick a model and enter your workload in millions of tokens. Rates are ₹21 input and ₹190 output per 1M.

Model

Input tokens (millions)Output tokens (millions)

Before GST: ₹590.00
Including 18% GST: ₹696.20

Pay as you go charges for actual tokens. If most of your use is on Qwen3.8-27B, compare your estimate with Pro at ₹2,499/month + GST or Team at ₹9,999/month + GST, which include it without a token charge.

Prepaid credit keeps spending bounded.

Top up in rupees and receive GST invoices.
Credit you buy never expires.
The minimum top-up is ₹500.
Pay-as-you-go calls stop at zero until you top up.

Dedicated

GPUs reserved for your workload in India.

Discuss a deployment →

Costs, credit and monthly limits

Understand the token calculation and what changes when you choose a monthly plan.

Discuss your requirements

What are the current pay-as-you-go rates?

On Qwen3.8-27B, pay ₹21 per million input tokens and ₹190 per million output tokens, before 18% GST. Other live models have their own rates in the per-model table; Decider is billed only for input tokens.

How much is 10M input and 2M output tokens?

That workload on Qwen3.8-27B costs ₹590.00 before GST, or ₹696.20 including GST.

What do Pro and Team include?

Pro: ₹2,499/month + GST for unlimited Qwen3.8-27B and ₹2,000 credit a month for every other model, 2 requests at once, 60 requests per minute and 1 API key. Team: ₹9,999/month + GST for unlimited Qwen3.8-27B and ₹8,000 credit a month for every other model, 8 requests at once, 200 requests per minute and up to 10 API keys. Unlimited applies to Qwen3.8-27B, which we host ourselves. It runs within your plan's request limits; when those are reached, further requests wait their turn. Other models, metered against your credit: DeepSeek V4.1 Flash, DeepSeek V4.1 Flash 1M, GLM-5.3 Flash, GLM-5.3, Gemma 4 31B IT, Gemma 4 26B A4B IT, Qwen3-Coder-Next, gpt-oss-120b, Nemotron 3.5 Super VL 120B A12B, Perplexity Decider v1.1 (27B), and the other models in the price table on /pricing. Included credit resets monthly and does not roll over. After your included credit, other models draw on your prepaid wallet. Calls to them stop at zero until you top up.

Is GST included in the displayed prices?

Displayed prices are before 18% GST. You receive GST invoices for your finance team to file and claim eligible input tax credit.

Does prepaid credit expire?

New accounts can use Qwen3.8-27B free for 15 days. Other models need a prepaid wallet, with a minimum top-up of ₹500. Credit you buy never expires. Included credit resets monthly and does not roll over.

Will calls keep running after credit reaches zero?

Pay-as-you-go calls stop when your prepaid wallet reaches zero. Top up before making further pay-as-you-go calls. Pro and Team still include unlimited Qwen3.8-27B.

How are dedicated deployments priced?

On-request models are deployed on GPUs in India for your workload and priced per deployment. Contact us with your application requirements.

Can I track costs separately for each client?

Yes. Create a key for each client and use the dashboard's spend-by-key view to track the corresponding usage.

Top up when you need more credit.

Add prepaid rupee credit in the console. Credit you buy never expires.

Open billing Read the API docs

Pay for what you use. Know it before you spend.

Start free. Add a plan when you need more.

Free Trial

Pro

Team

Other ways to buy

Pay as you go

Compare per-model token prices.

Processed in India

Processed in India or outside India

What would your token workload cost?

Estimate your token bill

Prepaid credit keeps spending bounded.

Dedicated

Costs, credit and monthly limits

Top up when you need more credit.

We use cookies