Skip to content
Rapid Router
Monthly index · CC BY 4.0

India AI API Price Index, October 2026

What 427 paid chat models cost from India this month, in rupees per million tokens.

Flagship models
input price $2 or more per 1M · 56 models
Cheapest
₹295
Qwen3.8 2.4T A95B
Median
₹553
per 1M blended
Mid-range models
input price $0.40 to $2 per 1M · 146 models
Cheapest
₹39.30
Chronos Hermes 13B V2
Median
₹123
per 1M blended
Small models
input price under $0.40 per 1M · 225 models
Cheapest
₹2.46
Llama 3.1 8B Instruct
Median
₹22.35
per 1M blended
Reasoning models
extended thinking supported · 234 models
Cheapest
₹5.40
Qwen3.7 Flash
Median
₹89.65
per 1M blended
Vision models
image input supported · 200 models
Cheapest
₹2.95
DeepSeek OCR 2
Median
₹83.51
per 1M blended
Open-weight models
Llama, Qwen, DeepSeek, Mistral, Kimi, GLM · 209 models
Cheapest
₹2.46
Llama 3.1 8B Instruct
Median
₹36.35
per 1M blended

Blended = 75% input price + 25% output price per million tokens, the mix of a typical chat or RAG workload. Each "Cheapest" figure is per 1M blended.

The 25 cheapest paid models this month

01Llama 3.1 8B Instruct₹1.97 in · ₹3.93 out · Meta₹2.46blended02Meta Llama 3.1 8B Instruct Turbo₹1.97 in · ₹3.93 out · Meta₹2.46blended03Phi 3 Medium 4K Instruct₹1.97 in · ₹3.93 out · Microsoft₹2.46blended04OpenChat 3.6 8B₹1.97 in · ₹3.93 out · OpenChat₹2.46blended05OpenChat 3.5₹1.97 in · ₹3.93 out · OpenChat₹2.46blended06Llama 3.1 8B Instruct₹1.97 in · ₹4.91 out · Novita AI₹2.70blended07Mistral Nemo Instruct 2407₹2.85 in · ₹2.95 out · Mistral₹2.87blended08DeepSeek OCR 2₹2.95 in · ₹2.95 out · Novita AI₹2.95blended09L3 8B Lunaris V1 Turbo₹3.93 in · ₹4.91 out · Sao10K₹4.18blended10Sao10K Stheno 8b₹4.91 in · ₹4.91 out · Novita AI₹4.91blended11Qwen3.7 Flash₹2.95 in · ₹12.77 out · Qwen₹5.40blended12Qwen3.7 Flash₹2.95 in · ₹12.77 out · Qwen₹5.40blended13GPT OSS 20B₹2.95 in · ₹13.76 out · OpenAI₹5.65blended14GLM-4.5-Air₹2.95 in · ₹13.76 out · Z.ai₹5.65blended15Mistral Small 3₹4.91 in · ₹7.86 out · Mistral₹5.65blended16Mixtral 8x7B Instruct v0.1₹4.91 in · ₹7.86 out · Mistral₹5.65blended17AutoGLM Phone 9B Multilingual₹3.44 in · ₹13.56 out · Novita AI₹5.97blended18Gemma 3 4B IT₹4.91 in · ₹9.83 out · Google₹6.14blended19GPT OSS 120B₹3.64 in · ₹16.70 out · OpenAI₹6.90blended20GPT OSS 120B Turbo₹3.64 in · ₹16.70 out · OpenAI₹6.90blended21CodeGemma 7B₹4.91 in · ₹14.74 out · Google₹7.37blended22Gemma 1.1 7B₹4.91 in · ₹14.74 out · Google₹7.37blended23Gemma 2 9B₹4.91 in · ₹14.74 out · Google₹7.37blended24Gemma 3 12B IT₹4.91 in · ₹14.74 out · Google₹7.37blended25Phi 4 Multimodal₹4.91 in · ₹14.74 out · Microsoft₹7.37blended

Flagships, priced in rupees

How to read this

Every number is a provider list price, the same figure a direct account with that provider would charge in dollars, converted to rupees at the rate Rapid Router bills at today. Paying from India through a provider directly adds a card forex markup and 18% GST under reverse charge on top of the dollar figure; through Rapid Router the GST is on the invoice and the platform fee is charged once when you buy credits, not per request.

Tiers are by input price: flagship at $2 or more per million, mid-range from $0.40, small below that. Reasoning and vision follow each model's published capabilities. Open-weight covers models whose weights are publicly released, whoever serves them. Free-tier models are excluded; they are listed on the free tier page.

To cite: "India AI API Price Index, October 2026, Rapid Router (rapidrouter.ai/price-index)". The underlying data is the catalog snapshot, refreshed on every release. For a monthly bill for your own volume, use the cost calculator.