OpenAI
gpt-oss-120b
Released 2025-08-05 · Knowledge up to 2024-06-30
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
You send / 1M
$0.150
tokens in
It replies / 1M
$0.600
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0005
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Near AI · fp4 | $0.030 | $0.150 | 100% | Read |
| Venice · int4 | $0.030 | $0.150 | 99% | Read |
| CoreWeave · fp4 | $0.030 | $0.170 | 100% | Read |
| DeepInfra · bf16 | $0.037 | $0.170 | 100% | Read |
| DekaLLM · bf16 | $0.030 | $0.180 | 100% | Read |
| AkashML · bf16 | $0.030 | $0.187 | 100% | Read |
| Crusoe · bf16 | $0.050 | $0.250 | 100% | Read |
| Mancer 2 · fp8 | $0.050 | $0.250 | 99% | Read |
| Novita · fp4 | $0.050 | $0.250 | 100% | Read |
| $0.090 | $0.360 | 5% | Read | |
| Sail Research · fp4 | $0.060 | $0.400 | 100% | Read |
| DigitalOcean | $0.060 | $0.420 | 100% | Read |
| BaseTen · fp4 | $0.100 | $0.500 | 99% | Read |
| BaseTen · fp4 | $0.100 | $0.500 | 99% | Read |
| Amazon Bedrock | $0.150 | $0.600 | 100% | Read |
| Nebius · fp4 | $0.150 | $0.600 | 100% | Read |
| Amazon Bedrock | $0.150 | $0.600 | 100% | Read |
| SiliconFlow · fp8 | $0.150 | $0.600 | 92% | Read |
| Phala | $0.150 | $0.600 | 99% | Read |
| Together | $0.150 | $0.600 | 100% | Read |
| Groq | $0.150 | $0.600 | 100% | Read |
| Mara | $0.150 | $0.750 | 94% | Read |
| Cerebras · fp16 | $0.350 | $0.750 | 100% | Read |
| Parasail · fp4 | $0.100 | $0.750 | 100% | Read |
| SambaNova | $0.140 | $0.950 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
- Repeated text is billed at $0.075 per 1M (prompt caching)
- Intelligence score: 11.6 / 100 (Artificial Analysis)
Similar models
- Solar Pro 4Upstage · $0.150 in / $0.600 out per 1M
- Hy3 previewTencent · $0.180 in / $0.600 out per 1M
- Solar Pro 3Upstage · $0.150 in / $0.600 out per 1M
- Hunyuan A13B InstructTencent · $0.140 in / $0.570 out per 1M
- Hy3Tencent · $0.132 in / $0.528 out per 1M
- LFM2.5-24B-A2BLiquid · $0.050 in / $0.700 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Reasoning AI ModelsTop No-Training Cheap Tool-Calling AI Models