> For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. > For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Pricing > Transparent pricing for all Sarvam AI services. View rates for chat completion, speech-to-text, text-to-speech, translation, and other Indian language AI APIs in Indian Rupees. Transparent pricing for all Sarvam AI services. All prices are in Indian Rupees (₹). ## Chat Completion #### Sarvam 105B **₹29.28 / ₹10.98 / ₹73.2 per 1M tokens**\ Chat completion. Input ₹29.28 · Cached input ₹10.98 · Output ₹73.2 — per 1M tokens. #### Sarvam 105B Chat **₹29.28 / ₹10.98 / ₹73.2 per 1M tokens**\ Chat completion (`sarvam-105b-conversations`). Input ₹29.28 · Cached input ₹10.98 · Output ₹73.2 — per 1M tokens. #### Gemma-4 31B **₹36.6 / ₹13.73 / ₹91.5 per 1M tokens**\ Chat completion (beta). Input ₹36.6 · Cached input ₹13.73 · Output ₹91.5 — per 1M tokens. #### GLM 5.2 **₹128.1 / ₹23.79 / ₹402.6 per 1M tokens**\ Chat completion (beta). Input ₹128.1 · Cached input ₹23.79 · Output ₹402.6 — per 1M tokens. GLM-5.2 and Gemma 4 31B are [available in beta](/api-reference/beta-apis) and rolling out gradually. GLM-5.2 reasons before every answer, and reasoning tokens are billed as output tokens — see [Reasoning](/api/getting-started/models/open-source/glm-5-2#reasoning) for how to budget `max_tokens`. ## Speech *Billed per second of audio* #### Speech to Text **₹30/hour**\ Charged per second of audio. Rounded up to the nearest second in each request. #### Speech to Text with Diarization **₹45/hour**\ Adds speaker identification. Rounded up to the nearest second in each request. #### Speech to Text & Translate **₹30/hour**\ Transcribes and translates. Rounded up to the nearest second in each request. #### Speech to Text, Translate & Diarization **₹45/hour**\ Transcribes, translates, and identifies speakers. Rounded up to the nearest second in each request. ## Language Tools *Billed per character* #### Sarvam Translate V1 **₹20/10K characters**\ Rounded up to the nearest character in each request. #### Translate Mayura V1 **₹20/10K characters**\ Rounded up to the nearest character in each request. #### Transliterate **₹20/10K characters**\ Rounded up to the nearest character in each request. #### Language Identification **₹3.5/10K characters**\ Rounded up to the nearest character in each request. ## Text to Speech #### Bulbul v2 **₹15/10K characters**\ Charged per character. Rounded up to the nearest character in each request. #### Bulbul v3 **₹30/10K characters**\ Beta pricing. Charged per character. Rounded up to the nearest character in each request. ## Document Digitization #### Document Digitization API **₹0.5/page**\ Extract structured data, tables, and text from documents with our powerful document parsing API. Maximum 10 pages per job. ## Pricing Summary | Service | Price | Billing Unit | Notes | | ---------------------------------------------- | ------------------------ | ------------------ | ---------------------------------------------------------------- | | **Chat Completion** | | | | | Sarvam 105B (`sarvam-105b`) | ₹29.28 / ₹10.98 / ₹73.2 | per 1M tokens | Input / Cached input / Output | | Sarvam 105B Chat (`sarvam-105b-conversations`) | ₹29.28 / ₹10.98 / ₹73.2 | per 1M tokens | Input / Cached input / Output | | Gemma-4 31B (`gemma4`) | ₹36.6 / ₹13.73 / ₹91.5 | per 1M tokens | Beta — Input / Cached input / Output | | GLM 5.2 (`glm5.2`) | ₹128.1 / ₹23.79 / ₹402.6 | per 1M tokens | Beta — Input / Cached input / Output; reasoning billed as output | | **Speech APIs** | | | | | Speech to Text | ₹30 | per hour | Billed per second | | Speech to Text + Diarization | ₹45 | per hour | Speaker identification | | Speech to Text + Translate | ₹30 | per hour | Transcription + translation | | Speech to Text + Translate + Diarization | ₹45 | per hour | All features combined | | **Language Tools** | | | | | Sarvam Translate V1 | ₹20 | per 10K characters | | | Translate Mayura V1 | ₹20 | per 10K characters | | | Transliterate | ₹20 | per 10K characters | | | Language Identification | ₹3.5 | per 10K characters | | | **Text to Speech** | | | | | Bulbul v2 | ₹15 | per 10K characters | | | Bulbul v3 | ₹30 | per 10K characters | | | **Document Digitization** | | | | | Document Digitization API | ₹0.5 | per page | Max 10 pages per job | ## Rate Limits by Plan Each plan includes account-level rate limits that apply across all APIs: | Plan | Rate Limit | Best For | | -------------- | ------------- | --------------------- | | **Starter** | 60 req/min | Prototyping & testing | | **Pro** | 200 req/min | Startups & POCs | | **Business** | 1,000 req/min | Production workloads | | **Enterprise** | Custom | Scale deployments | For full details including per-API limits, HTTP response headers, and error handling, see the [Credits & Rate Limits](/api/getting-started/ratelimits) page. --- ## Enterprise & Custom Pricing #### [Enterprise Solutions](/api/getting-started/help) Need custom rate limits, volume discounts, or dedicated support? Contact our team for enterprise pricing. #### [API Support](https://discord.com/invite/5rAsykttcs) Get technical support, integration help, and custom solutions from our developer team. --- **Free Credits:** Every new user receives ₹100 worth of free credits to explore all our APIs. Check our [Credits & Rate Limits](/api/getting-started/ratelimits) page for more details.