Language, image, speech and video models, served from India
One OpenAI-compatible endpoint for open-weight models running on our own GPUs in India. Prepaid in rupees with a GST invoice; prompts, images and audio never leave the country.
Drop-in for the OpenAI SDK
Change the base URL to https://api.bookmyhost.com/v1 and keep your code. Chat, embeddings, images, transcription and speech use the paths you already know.
Data stays in India
Requests are processed on GPUs we own and operate in India. Nothing is forwarded to a third-party model provider.
Rupee pricing, GST invoice
Pay per token, image, minute, character or second of video from a prepaid balance. No forex, no card surcharge, input tax credit on every invoice.
Chat, code, vision and embeddings
Priced per million tokens; input and output are charged separately.
| Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|
Llama 3.3 70Bllama-3.3-70b |
131,072 | ₹65 | ₹78 |
Sarvam-105Bsarvam-105b |
65,536 | ₹11.57 | ₹46.26 |
Qwen3 Coder 30Bqwen3-coder-30b |
65,536 | ₹16 | ₹64 |
Qwen2.5-VL 7B Instructqwen2.5-vl-7b-instruct |
98,304 | ₹21 | ₹21 |
Llama 3.1 8Bllama-3.1-8b |
98,304 | ₹11 | ₹11 |
Qwen3 8Bqwen3-8b |
40,960 | ₹4.5 | ₹15 |
BGE-M3bge-m3 |
8,192 | ₹1.1 | — |
MiniLM L6 v2all-minilm-l6-v2 |
256 | ₹1.5 | — |
Generate images and video, transcribe calls, speak text
Same API key and balance. Hindi and Hinglish speech is transcribed the way people type it.
| Model | What it does | Price |
|---|---|---|
FLUX.2 klein 4Bflux.2-klein-4b |
Fast text-to-image, 4-step. 1024x1024 in about two seconds. | ₹0.27 per image |
Whisper large-v3whisper-large-v3 |
Speech-to-text, 99 languages. Pass language=hi for Hindi in Devanagari. | ₹0.46 per minute of audio |
Whisper Hinglishwhisper-hinglish |
Hindi and code-mixed speech transcribed in Roman script, the way it is typed. | ₹0.46 per minute of audio |
Indic Parler-TTSindic-parler-tts |
Text to speech in Hindi and 20 other Indian languages plus Indian English, with named voices. | ₹2,313 per 1M characters |
CosyVoice 2cosyvoice-2 |
Text-to-speech with zero-shot voice cloning. | ₹2,313 per 1M characters |
LTX-2.5ltx-2.5 |
Text-to-video with synchronised sound, up to 10 seconds at 24 fps. | ₹11.57 per second of video |
Three calls, one key
Chat
curl https://api.bookmyhost.com/v1/chat/completions \
-H "Authorization: Bearer $KEY" \
-H "Content-Type: application/json" \
-d '{"model":"llama-3.3-70b",
"messages":[{"role":"user","content":"Namaste"}]}'Image
curl https://api.bookmyhost.com/v1/images/generations \
-H "Authorization: Bearer $KEY" \
-H "Content-Type: application/json" \
-d '{"model":"flux.2-klein-4b",
"prompt":"A tea stall at sunrise"}'Speech to text
curl https://api.bookmyhost.com/v1/audio/transcriptions \
-H "Authorization: Bearer $KEY" \
-F [email protected] \
-F model=whisper-hinglishStart with an API key
Pick a prepaid pack in the panel; the key works for every model on this page. Every new account starts with ₹200 of free credit.