Model reference · Synced 2025-04-29
GPT-OSS 120B
GPT-OSS 120B is an AI model from Nvidia. 128K context window. Capabilities: reasoning, tool calling, multimodal vision, open weights. Available on 34 providers. Cheapest listing: $0 input / $0 output per 1M tokens.
Quick facts
- Cheapest input: $0 per 1M tokens (Nvidia)
- Cheapest output: $0 per 1M tokens
- Context window: 128K tokens
- Max output: 8K tokens
- Release date: 2025-08-04
- Knowledge cutoff: 2025-08
- Capabilities: reasoning, tool calling, multimodal vision, open weights
- Provider count: 34
Provider pricing
Same model, different providers, different prices. Cheapest first.
| Provider | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Nvidia | $0 | $0 | 128K | 2025-08-04 |
| Cortecs | $0 | $0 | 128K | 2025-08-05 |
| Privatemode AI | $0 | $0 | 128K | 2025-08-04 |
| IO.NET | $0.04 | $0.4 | 131K | 2024-12-01 |
| NanoGPT | $0.05 | $0.25 | 128K | 2025-08-05 |
| Deep Infra | $0.05 | $0.24 | 131K | 2025-08-05 |
| DInference | $0.068 | $0.27 | 131K | 2025-08 |
| OpenRouter | $0.072 | $0.28 | 131K | 2025-08-05 |
| Abacus | $0.08 | $0.44 | 128K | 2025-08-05 |
| OVHcloud AI Endpoints | $0.09 | $0.47 | 131K | 2025-08-28 |
| Vertex | $0.09 | $0.36 | 131K | 2025-08-05 |
| submodel | $0.1 | $0.5 | 131K | 2025-08-23 |
| Baseten | $0.1 | $0.5 | 128K | 2025-08-05 |
| Synthetic | $0.1 | $0.1 | 128K | 2025-08-05 |
| DigitalOcean | $0.1 | $0.7 | 131K | 2025-08-05 |
| Vercel AI Gateway | $0.1 | $0.5 | 131K | 2025-08-05 |
| Scaleway | $0.15 | $0.6 | 128K | 2024-01-01 |
| Fireworks AI | $0.15 | $0.6 | 131K | 2025-08-05 |
| Weights & Biases | $0.15 | $0.6 | 131K | 2025-08-05 |
| Nebius Token Factory | $0.15 | $0.6 | 128K | 2026-01-10 |
| Amazon Bedrock | $0.15 | $0.6 | 128K | 2024-12-01 |
| FrogBot | $0.15 | $0.6 | 131K | 1970-01-01 |
| Vultr | $0.15 | $0.6 | 129K | 2025-08-05 |
| LLM Gateway | $0.15 | $0.75 | 131K | 2025-08-05 |
| Groq | $0.15 | $0.6 | 131K | 2025-08-05 |
| FastRouter | $0.15 | $0.6 | 131K | 2025-08-05 |
| Together AI | $0.15 | $0.6 | 131K | 2025-08-05 |
| evroc | $0.24 | $0.94 | 66K | 2025-08-05 |
| Cerebras | $0.25 | $0.69 | 131K | 2025-08-05 |
| Cloudflare AI Gateway | $0.35 | $0.75 | 128K | 2025-08-05 |
| Cloudflare Workers AI | $0.35 | $0.75 | 128K | 2025-08-05 |
| Berget.AI | $0.44 | $0.99 | 128K | 2025-08-05 |
| STACKIT | $0.49 | $0.71 | 131K | 2025-08-05 |
| Regolo AI | $1 | $4.2 | 128K | 2025-08-05 |
Prices synced daily from models.dev + provider docs.
How to use this model
If you're picking GPT-OSS 120B for a project, the three things that matter most:
- Compare it side-by-side with one or two alternatives in the live comparison tool. Pricing differences matter more than benchmarks at scale.
- Pick the cheapest provider that meets your latency / SLA need. Big spread across providers for the same weights.
- Re-evaluate every 3 months. Frontier prices drop fast; a model that's cheapest today may not be in a quarter.
Related models
FAQ
How much does GPT-OSS 120B cost? $0 input / $0 output per 1M tokens at the cheapest listing. See the table above for other providers.
What is the context window? 128K tokens.
Which providers offer it? Scaleway, NanoGPT, Abacus, submodel, OpenRouter, Fireworks AI, IO.NET, Weights & Biases, DInference, Deep Infra, and others — see the full table above.
Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.