Skip to content
Rapid Router
Free tool

AI API cost calculator in rupees.

Your tokens a month in, every model's cost in rupees out, at today's billing rate.
Presets
Cheapest for this workloadLlama 3.1 8B Instruct₹27.51 / month
ModelInput / 1MOutput / 1MPer month (INR)Per month (USD)
Llama 3.1 8B InstructMeta₹1.97₹3.93₹27.51$0.28
Meta Llama 3.1 8B Instruct TurboMeta₹1.97₹3.93₹27.51$0.28
Phi 3 Medium 4K InstructMicrosoft₹1.97₹3.93₹27.51$0.28
OpenChat 3.6 8BOpenChat₹1.97₹3.93₹27.51$0.28
OpenChat 3.5OpenChat₹1.97₹3.93₹27.51$0.28
Llama 3.1 8B InstructNovita AI₹1.97₹4.91₹29.48$0.30
Mistral Nemo Instruct 2407Mistral₹2.85₹2.95₹34.39$0.35
DeepSeek OCR 2Novita AI₹2.95₹2.95₹35.37$0.36
L3 8B Lunaris V1 TurboSao10K₹3.93₹4.91₹49.13$0.50
Qwen3.7 FlashQwen₹2.95₹12.77₹55.02$0.56
Qwen3.7 FlashQwen₹2.95₹12.77₹55.02$0.56
GPT OSS 20BOpenAI₹2.95₹13.76₹56.99$0.58
GLM-4.5-AirZ.ai₹2.95₹13.76₹56.99$0.58
Sao10K Stheno 8bNovita AI₹4.91₹4.91₹58.95$0.60
AutoGLM Phone 9B MultilingualNovita AI₹3.44₹13.56₹61.50$0.63
Mistral Small 3Mistral₹4.91₹7.86₹64.84$0.66
Mixtral 8x7B Instruct v0.1Mistral₹4.91₹7.86₹64.84$0.66
Gemma 3 4B ITGoogle₹4.91₹9.83₹68.77$0.70
GPT OSS 120BOpenAI₹3.64₹16.70₹69.76$0.71
GPT OSS 120B TurboOpenAI₹3.64₹16.70₹69.76$0.71
CodeGemma 7BGoogle₹4.91₹14.74₹78.60$0.80
Gemma 1.1 7BGoogle₹4.91₹14.74₹78.60$0.80
Gemma 2 9BGoogle₹4.91₹14.74₹78.60$0.80
Gemma 3 12B ITGoogle₹4.91₹14.74₹78.60$0.80
Phi 4 MultimodalMicrosoft₹4.91₹14.74₹78.60$0.80
Nemotron 3.5 Lightning 30B A3BFireworks AI₹4.91₹19.65₹88.42$0.90
Nemotron 3 Nano 30B A3BNVIDIA₹5.89₹15.72₹90.39$0.92
Nvidia Nemotron 3.5 LightningNVIDIA₹5.89₹15.72₹90.39$0.92
NVIDIA Nemotron Nano 9B v2NVIDIA₹5.89₹15.72₹90.39$0.92
Ling 3.0 Flash VLDeepInfra₹5.89₹17.68₹94.32$0.96
DeepSeek V3.1 TerminusDeepSeek₹5.89₹17.68₹94.32$0.96
DeepSeek V4 Flash 0731DeepSeek₹5.89₹17.68₹94.32$0.96
Ling 3.0 FlashinclusionAI₹5.89₹17.68₹94.32$0.96
Phi-4Microsoft₹6.88₹13.76₹96.29$0.98
Phi-4-reasoning-plusMicrosoft₹6.88₹13.76₹96.29$0.98
WizardLM 2 7BMicrosoft₹6.88₹13.76₹96.29$0.98
Qwen-VL OCRQwen₹6.88₹15.72₹100$1.02
Nemotron 3.5 Lightning 30B A3BNebius₹5.89₹23.58₹106$1.08
Granite 4.2 8BDeepInfra₹5.89₹24.56₹108$1.10
Gemma 2 27BGoogle₹7.86₹15.72₹110$1.12
Gemma 3 27B ITGoogle₹7.86₹15.72₹110$1.12
Devstral Small 2505Mistral₹7.37₹19.65₹113$1.15
Devstral SmallMistral₹7.37₹19.65₹113$1.15
Mistral 7B Instruct V0.1Mistral₹7.37₹19.65₹113$1.15
mistral-7b-instruct-v0.2Mistral₹7.37₹19.65₹113$1.15
Mistral-7B-Instruct-v0.3Mistral₹7.37₹19.65₹113$1.15
Mistral Small 3.1 24BMistral₹7.37₹19.65₹113$1.15
Mistral Small 3.2 24B Instruct 2506Mistral₹7.37₹19.65₹113$1.15
Qwen3.5 FlashQwen₹6.39₹25.55₹115$1.17
Qwen3.5 FlashQwen₹6.39₹25.55₹115$1.17
Ling 3.0 Flash FinNovita AI₹7.37₹21.61₹117$1.19
Ling 3.0 Flash SanteNovita AI₹7.37₹21.61₹117$1.19
Ling 3.0 Flash VLNovita AI₹7.37₹21.61₹117$1.19
Qwen 2 1.5B InstructArize AI₹9.83₹9.83₹118$1.20
Ministral 3 3BMistral₹9.83₹9.83₹118$1.20
Ministral 3B (latest)Mistral₹9.83₹9.83₹118$1.20
DeepSeek V4 FlashDeepSeek₹8.84₹17.68₹124$1.26
GPT-5 NanoOpenAI₹4.91₹39.30₹128$1.30
GPT-5 NanoOpenAI₹4.91₹39.30₹128$1.30
Qwen3.5 0.8BQwen₹9.83₹14.74₹128$1.30
Qwen3.5 2BQwen₹9.83₹14.74₹128$1.30
Qwen3.5 4BQwen₹9.83₹14.74₹128$1.30
Qwen3.5 9BQwen₹9.83₹14.74₹128$1.30
GPT OSS Safeguard 20BOpenAI₹7.37₹29.47₹133$1.35
Sky T1 32B PreviewNovaSky₹7.86₹27.51₹134$1.36
Qwen2.5-Coder 32B InstructQwen₹7.86₹27.51₹134$1.36
Qwen3 32BQwen₹7.86₹27.51₹134$1.36
QwQ 32BQwen₹7.86₹27.51₹134$1.36
GLM-4.6VZ.ai₹6.88₹33.41₹136$1.38
Gemma 4 31B It TurboGoogle₹8.84₹33.41₹155$1.58
Gemma 4 E4B ITGoogle₹8.84₹33.41₹155$1.58
Llama 3.2 90B Vision InstructMeta₹8.84₹33.41₹155$1.58
Llama-4-Maverick-17B-128E-Instruct-FP8Meta₹8.84₹33.41₹155$1.58
Llama 4 Maverick 17B 128e Instruct TurboMeta₹8.84₹33.41₹155$1.58
Qvq 72B PreviewQwen₹8.84₹33.41₹155$1.58
Llama 2 13B Chat HfMeta₹9.83₹29.47₹157$1.60
Llama 4 Scout 17B 16E InstructMeta₹9.83₹29.47₹157$1.60
Meta Llama 3 8B InstructMeta₹9.83₹29.47₹157$1.60
Airoboros 70BDeepInfra₹9.83₹31.44₹161$1.64
Llama 3.3 70B Instruct TurboDeepInfra₹9.83₹31.44₹161$1.64
Lzlv 70B Fp16 HfLizpreciatior₹9.83₹31.44₹161$1.64
Llama-3.3-70B-InstructMeta₹9.83₹31.44₹161$1.64
Nemotron 3 Super 120B A12BNVIDIA₹8.35₹39.30₹162$1.65
Qwen2 7B InstructQwen₹11.79₹23.58₹165$1.68
Qwen2.5 7B InstructQwen₹11.79₹23.58₹165$1.68
Qwen2.5 Coder 7BQwen₹11.79₹23.58₹165$1.68
Qwen3 14BQwen₹11.79₹23.58₹165$1.68
Seed 2.0 MiniDeepInfra₹9.83₹39.30₹177$1.80
Ministral 3 8BMistral₹14.74₹14.74₹177$1.80
Ministral 8B (latest)Mistral₹14.74₹14.74₹177$1.80
Voxtral SmallMistral₹9.83₹39.30₹177$1.80
Voxtral Small (latest)Mistral₹9.83₹39.30₹177$1.80
GPT-4.1 nanoOpenAI₹9.83₹39.30₹177$1.80
GPT-4.1 nanoOpenAI₹9.83₹39.30₹177$1.80
Qwen3.8 FlashDeepInfra₹11.10₹37.53₹186$1.89
Qwen Mt LiteQwen₹11.79₹35.37₹189$1.92
MiMo-V2.6-FlashDeepInfra₹13.76₹27.51₹193$1.96
MiMo-V2.6-FlashNovita AI₹13.76₹27.51₹193$1.96
Step 3.5 FlashStepFun₹13.76₹27.51₹193$1.96
Step 3.7 FlashStepFun₹13.76₹27.51₹193$1.96
MiMo-V2.5Xiaomi₹13.76₹27.51₹193$1.96
Claude Haiku 5.5Anthropic₹9.83₹49.13₹197$2.00
GPT-6 LunaOpenAI₹9.83₹49.13₹197$2.00
Qwen3 235B-A22BQwen₹8.84₹54.04₹197$2.00
Qwen3 235B A22B Instruct 2507Qwen₹8.84₹54.04₹197$2.00
Llama Guard 3 8BMeta₹17.68₹17.68₹212$2.16
Llama Guard 4 12BMeta₹17.68₹17.68₹212$2.16
Qwen3 30B A3BQwen₹11.79₹49.13₹216$2.20
Qwen3-Coder 30B-A3B InstructQwen₹11.79₹49.13₹216$2.20
Qwen3 30B A3B Instruct 2507Qwen₹12.77₹51.09₹230$2.34
Ministral 3 14BMistral₹19.65₹19.65₹236$2.40
Ministral 3 14BMistral₹19.65₹19.65₹236$2.40
Nemotron Content Safety 3.5NVIDIA₹19.65₹19.65₹236$2.40
Qwen3.8 FlashNovita AI₹14.74₹46.18₹240$2.44
Nemotron 3.5 Super VL 120B A12BDeepInfra₹14.74₹49.13₹246$2.50
GLM 5.3 FlashFireworks AI₹14.74₹49.13₹246$2.50
GLM-4.7-FlashZ.ai₹14.74₹49.13₹246$2.50
GLM-5.3-FlashZ.ai₹14.74₹49.13₹246$2.50
Qwen Mt FlashQwen₹15.72₹48.14₹253$2.58
Qwen-MT TurboQwen₹15.72₹48.14₹253$2.58

427 paid chat models (free-tier models are left out; see the free tier in the docs). Platform fee of 5% is charged once when you buy credits, not per request. Image, video and speech models are priced per unit on their own pages.

Common questions

How is the monthly cost calculated?
Input tokens per month × the model's input price per million, plus output tokens × the output price per million. Prices are the provider list prices Rapid Router bills at, converted to rupees at today's billing rate. The platform fee is charged once when you buy credits and is shown separately.
How many tokens is a page of text?
Roughly 1,300 tokens per 1,000 English words. Hindi and other Indic scripts tokenise less efficiently on most models, often 2 to 3 times more tokens for the same text.
Why do output tokens cost more than input?
Every provider prices generation higher than reading, usually 3 to 5 times. A workload that reads a lot and writes a little (search, classification, RAG) is cheaper per token than one that writes long answers.
Does the fee change the per-request price?
No. The per-request price is exactly the catalog price. The platform fee is added once when you buy credits, so the number this calculator shows is what your balance is debited.

Ready to try one? Create a key, point your SDK at https://rapidrouter.ai/api/v1, and the first requests are on the free daily allowance. See also: how to pay for AI APIs in rupees.