Explore models. Find your fit
Compare capabilities, pricing and independent benchmarks. Build with the model that fits your workload.
| Model | Deployment | Context | Input INR / 1M tokens | Cached input INR / 1M tokens | Output INR / 1M tokens |
|---|---|---|---|---|---|
| | Provisioned Throughput | 64K | ₹ 20.00 | - | - |
| | Provisioned Throughput | 1M | ₹ 115.00 | ₹ 4.00 | ₹ 350.00 |
| | Serverless | 1M | ₹ 14.00 | ₹ 0.25 | ₹ 55.00 |
| | Serverless | 1M | ₹ 25.00 | ₹ 0.50 | ₹ 105.00 |
| | Provisioned Throughput | 8K | ₹ 2.00 | - | - |
| | Serverless | 256K | ₹ 35.00 | ₹ 10.00 | ₹ 90.00 |
| | Serverless | 1M | ₹ 126.00 | ₹ 20.00 | ₹ 390.00 |
| | Serverless | 1M | ₹ 13.50 | ₹ 2.50 | ₹ 45.00 |
| | Provisioned Throughput | 1M | ₹ 200.00 | ₹ 20.00 | ₹ 950.00 |
| | Provisioned Throughput | 256K | ₹ 18.00 | ₹ 5.00 | ₹ 230.00 |
| | Serverless | 128K | ₹ 15.00 | ₹ 5.00 | ₹ 60.00 |
| | Serverless | 32K | ₹ 15.00 | ₹ 5.00 | ₹ 60.00 |
| | Serverless | 32K | ₹ 4.00 | - | - |
-
Clef Cloudflare · 64K context · Provisioned Throughput
- Input
- ₹20.00
- Cached input
- -
- Output
- -
-
DeepSeek V4 Pro DeepSeek · 1M context · Provisioned Throughput
- Input
- ₹115.00
- Cached input
- ₹4.00
- Output
- ₹350.00
-
DeepSeek V4.1 Flash 1017 Standard DeepSeek · 1M context · Serverless
- Input
- ₹14.00
- Cached input
- ₹0.25
- Output
- ₹55.00
-
DeepSeek V4.1 Flash 1017 Interactive DeepSeek · 1M context · Serverless
- Input
- ₹25.00
- Cached input
- ₹0.50
- Output
- ₹105.00
-
EmbeddingGemma 2 Google · 8K context · Provisioned Throughput
- Input
- ₹2.00
- Cached input
- -
- Output
- -
-
Gemma 4 31B Google · 256K context · Serverless
- Input
- ₹35.00
- Cached input
- ₹10.00
- Output
- ₹90.00
-
GLM 5.3 Z.ai · 1M context · Serverless
- Input
- ₹126.00
- Cached input
- ₹20.00
- Output
- ₹390.00
-
GLM 5.3 Flash Z.ai · 1M context · Serverless
- Input
- ₹13.50
- Cached input
- ₹2.50
- Output
- ₹45.00
-
Kimi K3.1 Pro Moonshot AI · 1M context · Provisioned Throughput
- Input
- ₹200.00
- Cached input
- ₹20.00
- Output
- ₹950.00
-
Qwen 3.8 27B Alibaba · 256K context · Provisioned Throughput
- Input
- ₹18.00
- Cached input
- ₹5.00
- Output
- ₹230.00
-
Sarvam 105B Sarvam · 128K context · Serverless
- Input
- ₹15.00
- Cached input
- ₹5.00
- Output
- ₹60.00
-
Sarvam 105B Conversations Sarvam · 32K context · Serverless
- Input
- ₹15.00
- Cached input
- ₹5.00
- Output
- ₹60.00
-
Sarvam Prism Sarvam · 32K context · Serverless
- Input
- ₹4.00
- Cached input
- -
- Output
- -
INR per 1M tokens, excluding GST.
Questions before you go live
Pricing is in INR per million tokens, excluding GST. Switch the currency to USD to see the same rates converted at ₹94 per US dollar. Each model has separate rates for input, cached input and output tokens.
Input tokens are sent to the model. Cached input covers eligible tokens reused from a cached prefix. Output tokens are generated by the model.
Yes. For reasoning models, reasoning tokens are billed at the model’s output rate.
Divide each token total by one million, multiply by the corresponding rate, then add the amounts. Use monthly totals for uncached input, cached input and output. GST is additional.
Yes. API credits are shared across models. Usage is charged at the input, cached input and output rates of the model you call.
Yes. The catalogue lists usage-based token rates for models served through Token Factory’s serverless API.
Token Factory guarantees 99.95% uptime, backed by an SLA. Contact the Sarvam team to discuss live traffic, latency targets and support requirements. Discuss SLA
Build with frontier open-weight models. Served from India.
Build with frontier open-weight models. Served from India.