Pricing calculator
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 ₹1,32,00,000/mo
on deepseek-v4-pro vs Nebius
12%
vs Nebius
Pick the model you use most
Choose a period, then a volume — or type your own
What share of your tokens are input rather than output
| Model | Context | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|---|
| vidman-adaptive | 1M | ₹42 – ₹120 | ₹13 | ₹127 – ₹384 |
| claude-opus-5 | 1M | ₹480 | ₹48 | ₹2400 |
| claude-sonnet-5 | 1M | ₹192 | ₹19 | ₹960 |
| deepseek-v4-flash | 128K | ₹10 | ₹1 | ₹24 |
| deepseek-v4-flash-0731 | 128K | ₹10 | ₹1 | ₹24 |
| deepseek-v4-pro | 128K | ₹134 | ₹13 | ₹326 |
| deepseek-v4-pro-0813 | 128K | ₹134 | ₹13 | ₹326 |
| deepseek-v4.1-flash | 1M | ₹38 | ₹8 | ₹154 |
| glm-5.2 | 1M | ₹134 | ₹13 | ₹326 |
| glm-5.3 | 1M | ₹134 | ₹25 | ₹422 |
| glm-5.3-flash | 1M | ₹14 | ₹3 | ₹48 |
| kimi-k2.7-code | 128K | ₹77 | ₹8 | ₹326 |
| kimi-k3 | 1M | ₹288 | ₹29 | ₹1440 |
| minimax-m3 | 128K | ₹29 | ₹3 | ₹115 |
| qwen3.5-397b-a17b | 256K | ₹48 | ₹5 | ₹326 |
| qwen3.8-2.4t-a95b | 256K | ₹192 | ₹19 | ₹576 |
All figures in ₹ per 1M tokens, current as of 21 September 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. Rupee prices use the fixed ₹96per USD commercial rate, effective 2026-09-21. All displayed INR rates and calculated totals round half-up to the nearest ₹1. 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.