LLMSarvam AI API pricing
10 Sarvam AI models. Source: https://docs.sarvam.ai/api/getting-started/pricing
- Provider type
- First-party
- Server location (where inference runs)
- India (Azure Central India; LLM inference on Yotta/NxtGen GPUs in India) · source
- Regions
- India
- Company HQ (secondary)
- India (outside EU) · Operated by Axonwise Private Limited (doing business as Sarvam AI), CIN U62099KA2023PTC176049, ROC Bangalore. Registered office: Urban Vault Indiranagar 732, 2nd Floor, Chinmaya Mission Hospital Road, Indiranagar 1st Stage, Bengaluru, Karnataka 560038, India. LEI 3358005G4HGT9LQVTE76 (MCA-corroborated). Checked 2026-11-09. · legal source
- EU data residency
- no
- Residency notes
- Trust Center: managed production on Microsoft Azure Central India; LLM inference on sovereign GPU infrastructure operated by Yotta and NxtGen in India. Token Factory: prompts run on Sarvam GPUs in India and are not sent to foreign model providers. Privacy Policy also allows cross-border transfers for some processing (US/EU vendors) with SCCs.
- Listing note
- Per-token Model API / Token Factory prices in INR excl. GST from docs.sarvam.ai. Serverless rows are generally available; Provisioned Throughput models are published at the same rates but enabled per organisation. Speech, TTS, translation, document and dubbing APIs are out of scope for this tracker. Sarvam Prism, Clef and EmbeddingGemma 2 are omitted (input-only / non-text generation).
- Residency source
- https://www.sarvam.ai/trust-center
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Tap a box to filter by it; tap it again to remove that filter. Filters combine.
10 of 10 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Sarvam AI First-party | GLM-5.3 Flash | ₹13.5 ≈ $0.1438 | ₹45 ≈ $0.4794 | ₹2.5 ≈ $0.0266 | ₹21.38 ≈ $0.2277 | 1.05M | no |
| Sarvam AI First-party | DeepSeek V4.1 Flash 1017 | ₹14 ≈ $0.1492 | ₹55 ≈ $0.586 | ₹0.25 ≈ $0.0027 | ₹24.25 ≈ $0.2584 | 1.05M | no |
| Sarvam AI First-party | Sarvam 105B | ₹15 ≈ $0.1598 | ₹60 ≈ $0.6393 | ₹5 ≈ $0.0533 | ₹26.25 ≈ $0.2797 | 131K | no |
| Sarvam AI First-party | Sarvam 105B Conversations | ₹15 ≈ $0.1598 | ₹60 ≈ $0.6393 | ₹5 ≈ $0.0533 | ₹26.25 ≈ $0.2797 | 33K | no |
| Sarvam AI First-party | DeepSeek V4.1 Flash 1017 Interactive | ₹25 ≈ $0.2664 | ₹105 ≈ $1.12 | ₹0.5 ≈ $0.0053 | ₹45 ≈ $0.4794 | 1.05M | no |
| Sarvam AI First-party | Gemma 4 31B | ₹35 ≈ $0.3729 | ₹90 ≈ $0.9589 | ₹10 ≈ $0.1065 | ₹48.75 ≈ $0.5194 | 262K | no |
| Sarvam AI First-party | Qwen 3.8 27B | ₹18 ≈ $0.1918 | ₹230 ≈ $2.45 | ₹5 ≈ $0.0533 | ₹71 ≈ $0.7565 | 262K | no |
| Sarvam AI First-party | DeepSeek V4 Pro | ₹115 ≈ $1.23 | ₹350 ≈ $3.73 | ₹4 ≈ $0.0426 | ₹173.75 ≈ $1.85 | 1.05M | no |
| Sarvam AI First-party | GLM-5.3 | ₹126 ≈ $1.34 | ₹390 ≈ $4.16 | ₹20 ≈ $0.2131 | ₹192 ≈ $2.05 | 1.05M | no |
| Sarvam AI First-party | Kimi K3.1 Pro | ₹200 ≈ $2.13 | ₹950 ≈ $10.12 | ₹20 ≈ $0.2131 | ₹387.5 ≈ $4.13 | 1.05M | no |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with €, CHF or ₹: those are as published and not converted. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09); sorting still uses the published ₹ amount. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. Click a header to sort.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.