Baseten
- Categories
- GPU clouds, Inference hosts
- Owned by
- (private)
- HQ
- US
- Website
- https://www.baseten.co
- Pricing page
- https://www.baseten.co/pricing/
- Fee model
- per_token+per_second_gpu
- Fees
- Model APIs per 1M tokens (input/cached/output). Dedicated deployments billed per minute: T4 $0.01052/min, L4 $0.01414, A10G $0.02012, A100 80GB $0.06667, H100 MIG 40GB $0.0625, H100 $0.10833, B200 $0.16633/min.
- OpenAI-compatible API
- yes
- Notes
- Model API catalogue is small (~16 models) and focused on large open models. Volume discounts available.
- Sources
- https://www.baseten.co/pricing/ collected 2026-09-18
LLM prices (13 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | $0.13 | $0.26 | $0.028 | — | ◐ src |
| DeepSeek V4 Pro 0423 | $1.74 | $3.48 | $0.145 | — | ◐ src |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | $0.132 | — | ◐ src |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.03 | — | ◐ src |
| GLM 4.7 | $0.60 | $2.20 | $0.12 | — | ◐ src |
| GLM-5.2 | $1.40 | $4.40 | $0.14 | — | ◐ src |
| GLM-5.3 | $1.40 | $4.40 | $0.14 | — | ◐ src |
| GLM-5.3 Flash | $0.15 | $0.50 | $0.03 | — | ◐ src |
| gpt-oss-120b | $0.10 | $0.50 | — | — | ◐ src |
| Kimi K2.6 | $0.95 | $4 | $0.16 | — | ◐ src |
| Kimi K2.7 Code | $0.95 | $4 | $0.16 | — | ◐ src |
| Kimi K3 | $3 | $15 | $0.30 | — | ◐ src |
| NVIDIA Nemotron 3 Ultra (Preview) | $0.60 | $2.40 | $0.12 | — | ◐ src |
GPU rates
| Provider | GPU | GPUs | VRAM/GPU | Billing | Per GPU-hr | Instance /hr | Region | Source |
|---|---|---|---|---|---|---|---|---|
| Baseten | T4 | 1 | 16 GB | serverless per sec | $0.631 | $0.631 | ✓ src ⓘ | |
| Baseten | L4 | 1 | 24 GB | serverless per sec | $0.848 | $0.848 | ✓ src ⓘ | |
| Baseten | A10G | 1 | 24 GB | serverless per sec | $1.21 | $1.21 | ✓ src ⓘ | |
| Baseten | A100 80GB | 1 | 80 GB | serverless per sec | $4 | $4 | ✓ src ⓘ | |
| Baseten | H100 | 1 | 80 GB | serverless per sec | $6.50 | $6.50 | ✓ src ⓘ | |
| Baseten | B200 | 1 | 180 GB | serverless per sec | $9.98 | $9.98 | ✓ src ⓘ |