Model
GPT OSS 120B
Open GPT reasoning model for self-hosted agents and controllable deployments
Compare providers (sorted by listed input price)
55 of 61 providers publish a price for GPT OSS 120B. The cheapest full-context option is LLM Gateway at $0.032/$0.14 per M. Listed prices span 50.3× for identical weights.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.032▼ 17.9%
- Best output /M
- $0.14▲ 40.0%
- Provider coverage
- 84
- 84 at the start · 24 snapshots
Price badge
https://www.vaanalytics.in/badge/openai/gpt-oss-120b.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- capabilityvia amazon-bedrock · Sep 13, 2026
- description: Open-weight GPT model for self-hosted reasoning and instruction-following workloads → Open GPT reasoning model for self-hosted agents and controllable deployments
- new modelvia amazon-bedrock · Sep 13, 2026
- repricedvia edenai · Sep 13, 2026
- input: $0.174 → $0.174
- output: $0.755 → $0.753
- repricedvia hyper · Sep 13, 2026
- input: $0.178 → $0.168
- output: $0.68 → $0.66
- cache_read: $0.089 → $0.084
- repricedvia edenai · Sep 13, 2026
- input: $0.174 → $0.174
- output: $0.697 → $0.696
- capabilityvia amazon-bedrock · Sep 13, 2026
- description: Open-weight GPT model for self-hosted reasoning and instruction-following workloads → Open GPT reasoning model for self-hosted agents and controllable deployments
Weights
Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.
licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.