# India AI model prices and cache | The Inference Directory

[Directory Indian Inference](/india/)

[Overview](/india/)[Models](/india/models/)[Compare prices](/india/models/compare/)

[Directories](/directories/) › [Indian Inference](/india/) › Model prices

Model prices

Input, cached input, and output rates in INR for every Indian model. Frontier models sort first. Missing cache prices stay visible as “-”.

All model families

**59** listings **42** families **20** frontier [Compare prices →](/india/models/compare/)

Search  Provider All providers E2E Networks BlazeJarvisLabsKrutrimNeevCloudSarvam AI Type All types DecisionLLMMultimodalOCRSTTTTSTranslationUtility  Frontier only Cache price published Sort Cheapest frontier Cheapest input Most providers Model A-Z

Showing 18 of 42 model families

 ![](/logos/models/deepseek.svg)DeepSeek V4.1 Flash Multimodal · 1M / 1.0M context

Frontier

Provider Input Cache Output

 [![](/logos/e2e-networks.png)E2E Networks Blaze DeepSeek V4.1 Flash ₹4.35 ₹0.58 ₹48.35](/india/providers/e2e-networks/)[ ![](/logos/jarvislabs.png)JarvisLabs DeepSeek V4.1 Flash ₹6.63 ₹0.28 ₹46.43 ](/india/providers/jarvislabs/)[ ![](/logos/sarvam-ai.png)Sarvam AI DeepSeek V4.1 Flash 1017 ₹25 ₹0.5 ₹105 ](/india/providers/sarvam-ai/)[ ![](/logos/jarvislabs.png)JarvisLabs DeepSeek V4.1 Flash Cyber ₹28.43 ₹0.57 ₹94.75](/india/providers/jarvislabs/)

per 1M tokens [Compare 3 providers →](/india/models/compare/?family=DeepSeek%20V4.1%20Flash)

 ![](/logos/models/qwen.svg)Qwen3.6 35B A3B Multimodal · 262K context

Frontier

Provider Input Cache Output

 [![](/logos/krutrim.png)Krutrim Qwen3.6-35B-A3B ₹7 \- ₹28](/india/providers/krutrim/)

per 1M tokens

 ![](/logos/models/zai.svg)GLM 5.3 Flash Multimodal · 1M / 1.3M context

Frontier

Provider Input Cache Output

 [![](/logos/e2e-networks.png)E2E Networks Blaze GLM 5.3 Flash ₹7.25 ₹1.45 ₹24.18](/india/providers/e2e-networks/)[ ![](/logos/jarvislabs.png)JarvisLabs GLM-5.3 Flash ₹13.27 ₹2.84 ₹42.64 ](/india/providers/jarvislabs/)[ ![](/logos/sarvam-ai.png)Sarvam AI GLM-5.3 Flash ₹13.5 ₹2.5 ₹45](/india/providers/sarvam-ai/)

per 1M tokens [Compare 3 providers →](/india/models/compare/?family=GLM%205.3%20Flash)

 ![](/logos/models/deepseek.svg)DeepSeek V4 Flash LLM · 1M context

Frontier

Provider Input Cache Output

 [![](/logos/jarvislabs.png)JarvisLabs DeepSeek V4 Flash ₹12.32 ₹2.84 ₹24.64](/india/providers/jarvislabs/)

per 1M tokens

 ![](/logos/models/xiaomi.svg)MiMo V2.6 Flash Multimodal · 1M context

Frontier

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI MiMo V2.6 Flash ₹12.5 ₹0.25 ₹25](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/qwen.svg)Qwen3.8 27B Multimodal · 256K / 128K context

Frontier

Provider Input Cache Output

 [![](/logos/jarvislabs.png)JarvisLabs Qwen 3.8 27B ₹28.43 ₹7.58 ₹222.66](/india/providers/jarvislabs/)[ ![](/logos/e2e-networks.png)E2E Networks Blaze Qwen3.8 27B ₹41.1 ₹8.22 ₹246.58](/india/providers/e2e-networks/)

per 1M tokens [Compare 2 providers →](/india/models/compare/?family=Qwen3.8%2027B)

 ![](/logos/models/xiaomi.svg)MiMo V2.6 Pro Multimodal · 1M context

Frontier

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI MiMo V2.6 Pro ₹40 ₹0.3 ₹80](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/zai.svg)GLM 5.2 LLM · 1M context

Frontier

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud GLM 5.2 ₹88.19 \- ₹284.5](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/zai.svg)GLM 5.3 LLM · 230K / 1M context

Frontier

Provider Input Cache Output

 [![](/logos/jarvislabs.png)JarvisLabs GLM-5.3 ₹114.65 ₹20.85 ₹365.74](/india/providers/jarvislabs/)[ ![](/logos/sarvam-ai.png)Sarvam AI GLM-5.3 ₹126 ₹20 ₹390](/india/providers/sarvam-ai/)

per 1M tokens [Compare 2 providers →](/india/models/compare/?family=GLM%205.3)

 ![](/logos/models/deepseek.svg)DeepSeek V4 Pro LLM · 1M context

Frontier

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI DeepSeek V4 Pro ₹115 ₹4 ₹350](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/moonshotai.svg)Kimi K3 Multimodal · 1M / 256K context

Frontier

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Kimi K3 ₹270 ₹27 ₹1350](/india/providers/sarvam-ai/)[ ![](/logos/neevcloud.png)NeevCloud Kimi K3 ₹284.5 \- ₹1422.48 ](/india/providers/neevcloud/)[ ![](/logos/e2e-networks.png)E2E Networks Blaze Kimi K3 ₹290.1 ₹58.02 ₹1450.5](/india/providers/e2e-networks/)

per 1M tokens [Compare 3 providers →](/india/models/compare/?family=Kimi%20K3)

 ![](/logos/sarvam-ai.png)Language identification Utility

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Language identification ₹0.35 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/sarvam-ai.png)Saaras v3 STT

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Saaras v3 ₹0.49 \- \-](/india/providers/sarvam-ai/)

per minute

 ![](/logos/sarvam-ai.png)Saaras v4 STT

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Saaras v4 ₹0.49 \- \-](/india/providers/sarvam-ai/)

per minute

 ![](/logos/sarvam-ai.png)Saarika v2.5 STT

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Saarika v2.5 ₹0.49 \- \-](/india/providers/sarvam-ai/)

per minute

 ![](/logos/sarvam-ai.png)Sarvam Vision , digitization OCR

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam Vision , digitization ₹0.5 \- \-](/india/providers/sarvam-ai/)

per\_page

D( Diarization (batch) STT

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Diarization (batch) ₹0.59 \- \-](/india/providers/sarvam-ai/)

per minute

 ![](/logos/sarvam-ai.png)Bulbul v4 Flash TTS

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Bulbul v4 Flash ₹1 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/sarvam-ai.png)Sarvam Vision , extraction OCR

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam Vision , extraction ₹1 \- \-](/india/providers/sarvam-ai/)

per\_page

IV Instant Voice Cloning TTS

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Instant Voice Cloning ₹2 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/sarvam-ai.png)Sarvam Translate / Mayura Translation

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam Translate / Mayura ₹2 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/sarvam-ai.png)Transliteration Translation

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Transliteration ₹2 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/sarvam-ai.png)Bulbul v3 TTS

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Bulbul v3 ₹3 \- \-](/india/providers/sarvam-ai/)

per 1k chars

 ![](/logos/models/google.svg)gemma-4-E4B-it Multimodal · 131K context

Legacy

Provider Input Cache Output

 [![](/logos/krutrim.png)Krutrim gemma-4-E4B-it ₹3 \- ₹8](/india/providers/krutrim/)

per 1M tokens

 ![](/logos/models/qwen.svg)Qwen3.5-9B Multimodal · 64K / 32K context

Legacy

Provider Input Cache Output

 [![](/logos/krutrim.png)Krutrim Qwen3.5-9B ₹3 \- ₹8](/india/providers/krutrim/)[ ![](/logos/e2e-networks.png)E2E Networks Blaze Qwen3.5-9B ₹9.67 ₹1.93 ₹14.5](/india/providers/e2e-networks/)

per 1M tokens

 ![](/logos/sarvam-ai.png)Sarvam Prism Decision

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam Prism ₹4 \- ₹0](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/meta.svg)Llama 3.1 8B Instant LLM · 131K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud Llama 3.1 8B Instant ₹4.83 \- ₹7.73](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/google.svg)Gemma 4 26B A4B Multimodal · 256K / 32K context

Legacy

Provider Input Cache Output

 [![](/logos/e2e-networks.png)E2E Networks Blaze Gemma 4 26B A4B ₹6.77 ₹1.35 ₹32.88](/india/providers/e2e-networks/)[ ![](/logos/krutrim.png)Krutrim gemma-4-26B-A4B-it ₹7 \- ₹28 ](/india/providers/krutrim/)[ ![](/logos/jarvislabs.png)JarvisLabs Gemma 4 26B A4B IT ₹10.42 ₹4.74 ₹35.06](/india/providers/jarvislabs/)

per 1M tokens

 ![](/logos/models/openai.svg)GPT OSS 20B LLM · 131K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud GPT OSS 20B ₹7.25 \- ₹28.99](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/qwen.svg)Qwen3 32B Multimodal · 64K context

Legacy

Provider Input Cache Output

 [![](/logos/e2e-networks.png)E2E Networks Blaze Qwen3 32B ₹7.74 ₹1.55 ₹27.08](/india/providers/e2e-networks/)

per 1M tokens

GP gpt-oss-20b LLM · 128K context

Legacy

Provider Input Cache Output

 [![](/logos/krutrim.png)Krutrim gpt-oss-20b ₹8 \- ₹32](/india/providers/krutrim/)

per 1M tokens

 ![](/logos/models/google.svg)Gemma 4 31B Multimodal · 256K / 100K context

Legacy

Provider Input Cache Output

 [![](/logos/krutrim.png)Krutrim gemma-4-31b-it ₹9 \- ₹33](/india/providers/krutrim/)[ ![](/logos/jarvislabs.png)JarvisLabs Gemma 4 31B IT ₹13.27 ₹4.74 ₹37.9 ](/india/providers/jarvislabs/)[ ![](/logos/neevcloud.png)NeevCloud Gemma 4 31B ₹18.97 \- ₹56.9 ](/india/providers/neevcloud/)[ ![](/logos/e2e-networks.png)E2E Networks Blaze Gemma 4 31B ₹29.01 ₹9.67 ₹120.88 ](/india/providers/e2e-networks/)[ ![](/logos/sarvam-ai.png)Sarvam AI Gemma 4 31B ₹35 ₹10 ₹90](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/openai.svg)GPT OSS 120B LLM · 128K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud GPT OSS 120B ₹9.66 \- ₹48.31](/india/providers/neevcloud/)[ ![](/logos/krutrim.png)Krutrim gpt-oss-120b ₹13 \- ₹65](/india/providers/krutrim/)

per 1M tokens

 ![](/logos/models/nvidia.svg)Nemotron 3.5 Super Multimodal · 1M context

Legacy

Provider Input Cache Output

 [![](/logos/jarvislabs.png)JarvisLabs Nemotron 3.5 Super VL 120B A12B ₹14.21 ₹1.89 ₹47.38](/india/providers/jarvislabs/)

per 1M tokens

 ![](/logos/sarvam-ai.png)Sarvam 105B LLM · 128K context

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam 105B ₹15 ₹5 ₹60](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/sarvam-ai.png)Sarvam 105B Conversations LLM · 32K context

Legacy

Provider Input Cache Output

 [![](/logos/sarvam-ai.png)Sarvam AI Sarvam 105B Conversations ₹15 ₹5 ₹60](/india/providers/sarvam-ai/)

per 1M tokens

 ![](/logos/models/deepseek.svg)DeepSeek-V3.2 LLM · 128K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud DeepSeek-V3.2 ₹27.05 \- ₹40.58](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/minimax.svg)MiniMax-M2.7 LLM · 205K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud MiniMax-M2.7 ₹28.99 \- ₹115.95](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/meta.svg)Llama 3.3 70B LLM · 131K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud Llama 3.3 70B ₹57.01 \- ₹76.33](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/zai.svg)GLM-4.7 LLM · 200K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud GLM-4.7 ₹57.97 \- ₹212.57](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/minimax.svg)MiniMax M3 Multimodal · 1M context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud MiniMax-M3 ₹57.97 \- ₹231.89](/india/providers/neevcloud/)

per 1M tokens

 ![](/logos/models/minimax.svg)MiniMax-M2.7-highspeed LLM · 205K context

Legacy

Provider Input Cache Output

 [![](/logos/neevcloud.png)NeevCloud MiniMax-M2.7-highspeed ₹57.97 \- ₹231.89](/india/providers/neevcloud/)

per 1M tokens

No models match. Clear a filter or search another term.

Load more model families

Provider rows show input, cached input, and output prices in the provider's currency. Compare opens only for model families with more than one provider.