Offering overview
Dedicated Inference is the flagship: custom, fine-tuned or open-source models run on autoscaling GPU deployments with per-minute billing, while Model APIs give instant access to pre-optimised endpoints for GLM, DeepSeek, Kimi, NVIDIA Nemotron and gpt-oss. Chains compose multi-model pipelines, and a dedicated embeddings runtime handles retrieval workloads alongside transcription, image generation and text-to-speech. Training via the Loops SDK brings reinforcement learning onto the same stack. Enterprises can choose fully managed cloud with optional single-tenant clusters, self-hosted deployment inside their own VPCs, or hybrid mode that bursts to Baseten capacity, backed by SOC 2 Type II and HIPAA compliance and forward-deployed engineers. AI product companies and enterprises that need reliable, low-latency serving without building an inference team are the target; the company is headquartered in San Francisco. GPU pricing starts at $0.01052 per minute for an NVIDIA T4 (roughly $0.63 per hour), with H100 at $0.10833 per minute; Model API rates begin at $0.10 per million input tokens for OpenAI GPT OSS 120B.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- Model Inference, Model Training, Fine-Tuning, AI Applications, AI Agents, Vector Search
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- GLM-5.3, GLM-5.2, DeepSeek V4, DeepSeek V4.1 Flash, Kimi K3, NVIDIA Nemotron 3 Ultra, gpt-oss-120B
- AI frameworks
- Not stated
- Inference endpoints
- Unknown
- Fine-tuning
- Unknown
- Vector database
- Unknown
- Model catalog
- Unknown
- Monitoring
- Not stated
- Evaluation
- Not stated
Security & compliance
No controls are stated.
Geography
Provider headquarters are separate from offering infrastructure and availability.
Infrastructure regions
Not stated
Data-residency jurisdictions
Not stated
Service availability
Not stated
Support coverage
Not stated
Available plans
Pricing can change. Promotional prices are shown separately from standard prices.
| Plan | Price | Compute | Storage | GPU | Price checked | Actions |
|---|---|---|---|---|---|---|
| Baseten Inference PlatformNot stated | $0.01Usage Only | Unknown — RAM | Unknown | No | 7 October 2026 |
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Unverified
- Primary source
- baseten.co
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 7 October 2026