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-5-5 | 1M | ₹384 | ₹19 | ₹1,920 |
| claude-sonnet-5-5 | 1M | ₹192 | ₹9.60 | ₹960 |
| claude-opus-5 | 1M | ₹480 | ₹48 | ₹2,400 |
| claude-sonnet-5 | 1M | ₹192 | ₹19 | ₹960 |
| gpt-6-astra | 266K | ₹960 | ₹96 | ₹4,800 |
| gpt-6-sol | 266K | ₹192 | ₹19 | ₹960 |
| gpt-6-luna | 266K | ₹9.60 | ₹0.96 | ₹48 |
| gpt-5.6-sol | 266K | ₹384 | ₹38 | ₹1,920 |
| gpt-5.6-terra | 266K | ₹192 | ₹19 | ₹1,152 |
| gpt-5.6-luna | 266K | ₹19 | ₹1.92 | ₹115 |
| gpt-5.5 | 266K | ₹480 | ₹48 | ₹2,880 |
| gpt-5.4 | 266K | ₹240 | ₹24 | ₹1,440 |
| gpt-5.4-mini | 266K | ₹72 | ₹7.20 | ₹432 |
| gpt-5.4-nano | 266K | ₹19 | ₹1.92 | ₹120 |
| gpt-5.1 | 266K | ₹120 | ₹12 | ₹960 |
| gpt-5 | 266K | ₹120 | ₹12 | ₹960 |
| gpt-5-mini | 266K | ₹24 | ₹2.40 | ₹192 |
| gpt-5-nano | 266K | ₹4.80 | ₹0.48 | ₹38 |
| gpt-4.1 | 1M | ₹192 | ₹48 | ₹768 |
| gpt-4.1-mini | 1M | ₹38 | ₹9.60 | ₹154 |
| gpt-4.1-nano | 1M | ₹9.60 | ₹2.40 | ₹38 |
| gpt-4o | 125K | ₹240 | ₹120 | ₹960 |
| gpt-4o-mini | 125K | ₹14 | ₹7.20 | ₹58 |
| o4-mini | 195K | ₹106 | ₹26 | ₹422 |
| o3 | 195K | ₹192 | ₹48 | ₹768 |
| o3-mini | 195K | ₹106 | ₹53 | ₹422 |
| openai/chat-latest | 266K | ₹480 | ₹48 | ₹2,880 |
| deepseek-v4.1-flash | 1M | ₹38 | ₹3.84 | ₹154 |
| deepseek-v4-pro | 128K | ₹134 | ₹13 | ₹326 |
| deepseek-v4-pro-0813 | 128K | ₹134 | ₹13 | ₹326 |
| deepseek-v4-flash | 128K | ₹9.60 | ₹0.96 | ₹24 |
| deepseek-v4-flash-0731 | 128K | ₹9.60 | ₹0.96 | ₹24 |
| minimax-m3 | 128K | ₹29 | ₹2.88 | ₹115 |
| kimi-k3 | 1M | ₹288 | ₹29 | ₹1,440 |
| kimi-k2.7-code | 128K | ₹77 | ₹7.68 | ₹326 |
| qwen3.8-2.4t-a95b | 256K | ₹192 | ₹19 | ₹576 |
| qwen3.5-397b-a17b | 256K | ₹48 | ₹4.80 | ₹326 |
| glm-5.3 | 1M | ₹134 | ₹25 | ₹422 |
| glm-5.3-flash | 1M | ₹14 | ₹2.88 | ₹48 |
| glm-5.2 | 1M | ₹134 | ₹13 | ₹326 |
| claude-haiku-5-5 | 1M | ₹9.60 | ₹0.96 | ₹48 |
All figures in ₹ per 1M tokens, current as of 16 October 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 convert at the platform exchange rate billing uses, ₹96 per USD today; calculated totals round 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.