GPT OSS 120B API pricing
GPT OSS 120B by Baseten costs $0.10 per 1M input tokens and $0.50 per 1M output tokens (1M in + 1M out = $0.60).
- API model id
GPT OSS 120B- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Cached input / 1M
- —
- Context window
- —
- Notes
- Baseten Model APIs (shared, pre-optimized endpoints). 'Fast' variants cost more.
- Source
- https://www.baseten.co/pricing/
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Model API regions not stated on the pricing page. Enterprise plan advertises 'full control over data residency' and custom global regions (dedicated/self-hosted deployments).
- Last verified
- 2026-10-15
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Baseten | GPT OSS 120B | $0.23 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Baseten models
- GLM-5.3: $1.40 / $4.40
- GLM-5.3-Flash: $0.15 / $0.50
- GLM-5.2: $1.40 / $4.40
- DeepSeek V4.1 Flash: $0.30 / $1.20
- DeepSeek-V4-Flash-0731: $0.13 / $0.26
- DeepSeek V4 Pro 0813: $1.32 / $3.96
- Kimi K3: $3.00 / $15.00