Pricing calculator

Price your inference bill before you spend it

Choose a model, dial in your traffic, and read the daily, weekly or monthly figure — beside what Fireworks, Together AI and Nebius would take for the same job. Our side of the table is the committed rate card; the rivals are dated snapshots.

Save ₹1,30,00,625/mo

on deepseek-v4-pro vs Nebius

12%

vs Together AI

12%

vs Nebius

Pick the model you use most

Choose a period, then a volume — or type your own

tokens/mo

What share of your tokens are input rather than output

Input 70%Output 30%

Based on 500 billion tokens/mo · 350 billion input, 150 billion output

Input / 1MOutput / 1MMonthly
Vidman AI₹132.37₹321.47₹9,45,50,000
Together AI₹164.52₹329.03₹10,69,36,050
Nebius₹165.46₹330.93₹10,75,50,625

Together AI serverless, as published 29 August 2026.

Get 50% extra on your first wallet top-up.

Billed per second of GPU time.

Per-million-token rates

ModelContextInput / 1MCached / 1MOutput / 1M
vidman-adaptive1M₹41.60 – ₹118.19₹13.24₹124.81 – ₹373.47
claude-opus-51M₹472.75₹47.28₹2363.75
claude-sonnet-51M₹189.10₹18.91₹945.50
deepseek-v4-flash128K₹9.46₹0.95₹23.64
deepseek-v4-flash-0731128K₹9.46₹0.95₹23.64
deepseek-v4-pro128K₹132.37₹13.24₹321.47
deepseek-v4-pro-0813128K₹132.37₹13.24₹321.47
glm-5.21M₹132.37₹13.24₹321.47
glm-5.31M₹132.37₹24.58₹416.02
glm-5.3-flash1M₹14.18₹2.84₹47.28
kimi-k2.7-code128K₹75.64₹7.56₹321.47
kimi-k31M₹283.65₹28.37₹1418.25
minimax-m3128K₹28.37₹2.84₹113.46
qwen3.5-397b-a17b256K₹47.28₹4.73₹321.47
qwen3.8-2.4t-a95b256K₹189.10₹18.91₹567.30

All figures in ₹ per 1M tokens, current as of 29 August 2026. Vidman AI Adaptive quotes a band because each request is billed at the model that served it; pinned models list their floor rate. Prompt caching bills separately. The dashboard shows the exact rate before a call goes out — that number wins over this table. ₹ prices use ₹94.55 per USD (committed rate, 2026-09-07 — live rate unavailable)— the same figure every ₹ above was converted at. Inference, fine-tuning, training, and dedicated hosting all run inside India.

Neither product can put you in the red. Both spend from the same pre-paid wallet. At zero balance you get a grace warning, and a running endpoint pauses instead of stacking charges. Top up and it resumes.