BaseTen
BaseTen serves 11 open models from 5 labs on OpenRouter, in 13 offers. Of the 11 models it shares with other providers, it has the lowest blended price on 0. Its median blended price is $0.525 (₹50) per million tokens, blended 3:1 input to output. Its most common precision is 4-bit (5 of 13 offers).
Company and policies
- Headquarters listed by OpenRouter
- United States
- Datacenter countries listed by OpenRouter
- Not listed
Privacy policyTerms of serviceService statusProvider on OpenRouter
Provider-level locations do not guarantee where a particular request is processed. Check the provider's terms for data handling. Directory source, checked 14 Nov 2026.
Precision and price rank
| Offers | 4-bit | 8-bit | Other | Not listed | Total |
|---|---|---|---|---|---|
| Offers | 5 | 5 | 1 | 2 | 13 |
| Rank | Models |
|---|---|
| Lowest or tied | 0 |
| 2nd | 0 |
| 3rd | 1 |
| 4th or lower | 10 |
Every model BaseTen serves 13
USD and INR per million tokens| Precision | Lab | Pricing | ||||||
|---|---|---|---|---|---|---|---|---|
| $0.1625₹15 | $0.13₹12 | $0.26₹25 | 6 of 23 | 1,048,576 | FP32 | DeepSeek | All providers | |
| $0.1625₹15 | $0.13₹12 | $0.26₹25 | 6 of 23 | 1,048,576 | FP8 | DeepSeek | All providers | |
| $1.98₹187 | $1.32₹124 | $3.96₹373 | 12 of 20 | 1,048,576 | FP4 | DeepSeek | All providers | |
| $0.525₹50 | $0.30₹28 | $1.20₹113 | 22 of 28 | 1,048,576 | Not listed | DeepSeek | All providers | |
| $0.525₹50 | $0.30₹28 | $1.20₹113 | 31 of 38 | 1,048,576 | Not listed | DeepSeek | All providers | |
| $2.15₹203 | $1.40₹132 | $4.40₹415 | 15 of 24 | 1,048,576 | FP8 | Z.ai (Zhipu) | All providers | |
| $2.15₹203 | $1.40₹132 | $4.40₹415 | 26 of 37 | 1,048,576 | FP4 | Z.ai (Zhipu) | All providers | |
| $3.225₹304 | $2.10₹198 | $6.60₹622 | 37 of 37 | 1,048,576 | FP8 | Z.ai (Zhipu) | All providers | |
| $0.2375₹22 | $0.15₹14 | $0.50₹47 | 22 of 37 | 1,048,576 | FP8 | Z.ai (Zhipu) | All providers | |
| $0.20₹19 | $0.10₹9.43 | $0.50₹47 | 13 of 22 | 128,072 | FP4 | OpenAI | All providers | |
| $6.00₹566 | $3.00₹283 | $15.00₹1,414 | 11 of 20 | 1,048,576 | FP8 | Moonshot AI | All providers | |
| $1.05₹99 | $0.60₹57 | $2.40₹226 | 3 of 4 | 202,800 | FP4 | NVIDIA | All providers | |
| $0.275₹26 | $0.20₹19 | $0.50₹47 | 8 of 10 | 1,048,576 | FP4 | NVIDIA | All providers |
Where BaseTen is cheapest
0 of 11 models shared with other providersBaseTen does not have the lowest blended price on any model that other providers also serve.
BaseTen questions
Which open models does BaseTen serve?
BaseTen serves 11 open models from 5 labs on OpenRouter. The most downloaded on Hugging Face are GLM-5.3-Flash, gpt-oss-120b and DeepSeek-V4-Flash-0731. Prices were fetched 14 Nov 2026.
Is BaseTen the cheapest provider for any open model?
No. Its best position is 3rd of 4 providers, for NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 at $1.05 (₹99) per million tokens, blended 3:1 input to output.
What precision does BaseTen serve models at?
Of its 13 offers, BaseTen lists 4-bit for 5, 8-bit for 5 and Other for 1, and no precision for 2. Prices are in US dollars; we show rupees at ₹94.29 per $1.
About this data
Every number on this page comes from the endpoints OpenRouter lists for each model, fetched 14 Nov 2026. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.