One key. Every model. No forex markup.
18 models · 5 categories · All prices in ₹ INR
Mistral 7B Instruct
Fast, multilingual 7B model ideal for chat, text generation, and classification. Available on every plan with ₹0.02/1K tokens.
Mistral Nemo 12B
Mistral's 12B model with 128K context. Strong multilingual support for chat and instruction-following tasks.
GPT OSS 20B
OpenAI's 20B open-source model with strong reasoning capabilities. Low input cost at ₹0.01/1K tokens.
Mistral Small 24B
Mistral's 24B model with 128K context. Balances quality and speed for multilingual chat and content tasks.
Qwen3.6 27B
Alibaba's 27B multimodal model with 128K context. Handles image understanding alongside chat and function calling.
Qwen3 Coder 30B
Alibaba's 30B code-specialised model with 128K context. Excellent for code generation, debugging, and technical tasks at ₹0.01/1K input.
Llama 3.3 70B Instruct
Meta's flagship 70B model with 128K context. Top-tier multilingual performance for complex chat, analysis, and generation tasks.
GPT OSS 120B
OpenAI's 120B open-source reasoning model. Exceptional depth for complex problem-solving. Requires Pro plan or above.
Qwen2.5 VL 72B
Alibaba's 72B vision-language model with 128K context. Processes images alongside text for multimodal understanding. Pro plan required.
Qwen3.5 397B
Alibaba's 397B MoE model with 256K context. Massive capacity for complex chat and function calling. Pro plan required.
Gemma 4 26B
Google's Gemma 4 26B A4B — a multimodal MoE model (25.2B total, 3.8B active) with text, image, and video input, a 256K context, and native function calling, at ₹0.02/1K input.
PaddleOCR-VL
PaddleOCR-VL 1.6 — document parsing model scoring 96.33% on OmniDocBench v1.6. Handles text, tables, formulas, seals, and stamps across 109 languages via chat/completions at ₹0.02/1K tokens.
BGE Multilingual Gemma2
Multilingual embedding model combining BGE and Gemma2. Ideal for semantic search, RAG, and text classification at ₹0.01/1K tokens.
Qwen3 Embedding 4B
Alibaba's Qwen3-Embedding-4B — multilingual embedding model with configurable output dimensions (32-2560) across 100+ languages, at ₹0.02/1K tokens.
Stable Diffusion XL
Stability AI's SDXL for text-to-image generation. Free on nabh.cloud — no wallet deduction, subject to standard rate limits.
Whisper Large v3
OpenAI's Whisper Large v3 — automatic speech recognition and translation, trained on 5M+ hours of audio. Supports 99 languages (Apache 2.0), billed at ₹0.35/min.
Whisper Large v3 Turbo
Pruned, finetuned Whisper Large v3 — decoding layers cut from 32 to 4 for meaningfully faster transcription. Supports 99 languages (MIT), billed at ₹0.35/min.
Kokoro TTS
Kokoro-82M — a lightweight, 82M-parameter open-weight TTS model with 54 voices across 8 languages. Apache 2.0, billed at ₹0.15/1K characters.