# Baseten

Canonical: https://inetgeek.com/llm-apis/baseten/

Model inference platform with per-token APIs for open models and dedicated deployments billed by the minute.

## Who it suits

Teams that want per-token APIs and dedicated GPUs from one vendor with no plan fee — minute-granularity billing means a model that runs for ten minutes costs ten minutes.

Consider something else if Its dedicated H100 works out at $6.50 an hour, roughly three times DeepInfra's, so steady GPU workloads pay a premium for the platform around them.

## What the documentation says

### Pricing

- Entry paid plan: $0 per month on the Basic plan — pay as you go, with dedicated deployments, model APIs and training included rather than gated behind a fee. ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Pricing model: No platform fee: per-token Model APIs for open models, and dedicated deployments billed per minute of compute with volume discounts. The Pro tier buys priority access to high-demand GPUs rather than a lower rate. ([source](https://www.baseten.co/pricing/), read 2026-09-06)

### Inference

- Input price, top model: $1.40 per million input tokens for GLM-5.3, with cached input at $0.14 and output at $4.40. GLM-5.2 Fast, a speed variant, is $2.10. ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Output price, top model: $4.40 per million output tokens for GLM-5.3. ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Input price, cheapest model: $0.10 per million input tokens for GPT OSS 120B, with output at $0.50. GLM-5.3-Flash is $0.15 in and $0.50 out. ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Context window: 1,048K tokens on the DeepSeek V4 line and the GLM 5.2/5.3 family, the widest it serves; 262K on the Kimi K2 models, 200K on GLM 4.7 and 128K on GPT OSS 120B. Baseten's table publishes these in thousands, so the magnitude is 1,048,000 rather than the 1,048,576 a power-of-two reading would give — the vendor's own figure, not a conversion of it. ([source](https://docs.baseten.co/inference/model-apis/overview), read 2026-09-08)
- Max output tokens: 262K tokens on most models, and it is a separate ceiling from the context window rather than the remainder of it: DeepSeek V4 Flash 0731 allows 384K output inside a 1,048K window, while GLM 4.7, Nemotron Ultra and GPT OSS 120B cap output at their full context. The Inkling models are the outlier at 32K. ([source](https://docs.baseten.co/inference/model-apis/overview), read 2026-09-08)
- Prompt caching: Supported ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Rate limits: Two limits, requests and tokens per minute, set by account status rather than spend: an unverified Basic account gets 15 RPM and 100,000 TPM, a verified Basic or Pro account 120 RPM and 500,000 TPM, Enterprise custom. Cached input counts toward TPM at full weight even though it is billed cheaper. ([source](https://docs.baseten.co/inference/model-apis/pricing-and-limits), read 2026-09-07)

### GPU

- H100 SXM, per GPU-hour: $6.50 per hour for a dedicated H100 80GB. Baseten publishes $0.10833 per MINUTE — the hourly figure is that times 60, ours rather than Baseten's, and the page offers an hourly toggle. A100 80GB is $0.06667 a minute and B200 $0.16633. ([source](https://www.baseten.co/pricing/), read 2026-09-06)
- Largest GPU offered: 180GB per GPU on a B200, at $0.16633 per minute — $9.98 an hour. ([source](https://www.baseten.co/pricing/), read 2026-09-06)

## Compared with

- [Baseten vs DeepInfra](https://inetgeek.com/compare/deepinfra-vs-baseten/)
- [Baseten vs Fireworks AI](https://inetgeek.com/compare/baseten-vs-fireworks/)
- [Baseten vs Anthropic](https://inetgeek.com/compare/baseten-vs-anthropic/)
- [Baseten vs Novita AI](https://inetgeek.com/compare/baseten-vs-novita/)