gpt-oss-120b
by OpenAI · openai/gpt-oss-120b
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...
- Input / 1M tokens
- $0.15
- Output / 1M tokens
- $0.60
- Context
- 131K
Specs
| Input price | $0.15 / 1M tokens |
|---|---|
| Output price | $0.60 / 1M tokens |
| Cached input | $0.075 / 1M tokens |
| Context window | 131K tokens |
| Max output | 65.5K tokens |
| Reads | text |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 5, 2025 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
26 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Near AI | fp4 | 131K | 118K | $0.03 | $0.15 | $0.015 | 100% | 774 ms | 36 tok/s | Normal | |
| Venice | int4 | 128K | 32.8K | $0.03 | $0.15 | $0.03 | 100% | 2.05 s | 25 tok/s | Normal | |
| CoreWeave | fp4 | 131K | 118K | $0.03 | $0.17 | $0.03 | 100% | 306 ms | 61 tok/s | Normal | |
| DeepInfra | bf16 | 131K | 118K | $0.037 | $0.17 | — | 100% | 475 ms | 30 tok/s | Normal | |
| DekaLLM | bf16 | 131K | 118K | $0.03 | $0.18 | $0.03 | 100% | 554 ms | 60 tok/s | Normal | |
| AkashML | bf16 | 131K | 118K | $0.03 | $0.187 | $0.03 | 100% | 354 ms | 105 tok/s | Normal | |
| Crusoe | bf16 | 131K | 118K | $0.05 | $0.25 | $0.05 | 100% | 234 ms | 238 tok/s | Normal | |
| Mancer 2 | fp8 | 131K | 118K | $0.05 | $0.25 | — | 100% | 915 ms | 43 tok/s | Normal | |
| Novita | fp4 | 131K | 32.8K | $0.05 | $0.25 | — | 100% | 766 ms | 104 tok/s | Normal | |
| — | 131K | 118K | $0.09 | $0.36 | — | 0% | 669 ms | 95 tok/s | Code -5 | ||
| Sail Research | fp4 | 131K | 118K | $0.06 | $0.40 | $0.03 | 100% | 615 ms | 128 tok/s | Normal | |
| DigitalOcean | — | 128K | 4.1K | $0.06 | $0.42 | $0.012 | 100% | 617 ms | 46 tok/s | Normal | |
| BaseTen | fp4 | 128K | 115K | $0.10 | $0.50 | $0.10 | 100% | 152 ms | 158 tok/s | Normal | |
| BaseTen | fp4 | 128K | 115K | $0.10 | $0.50 | $0.10 | 100% | 197 ms | 157 tok/s | Normal | |
| Amazon Bedrock | — | 131K | 118K | $0.15 | $0.60 | — | 100% | 463 ms | 160 tok/s | Normal | |
| Amazon Bedrock | — | 131K | 118K | $0.15 | $0.60 | — | 100% | 424 ms | 173 tok/s | Normal | |
| Groq | — | 131K | 65.5K | $0.15 | $0.60 | $0.075 | 100% | 175 ms | 323 tok/s | Normal | |
| Nebius | fp4 | 131K | 118K | $0.15 | $0.60 | $0.10 | 100% | 272 ms | 289 tok/s | Normal | |
| Phala | — | 131K | 32.8K | $0.15 | $0.60 | — | 100% | 993 ms | 104 tok/s | Normal | |
| SiliconFlow | fp8 | 131K | 8.19K | $0.15 | $0.60 | $0.075 | 100% | 1.19 s | 46 tok/s | Normal | |
| Together | — | 131K | 118K | $0.15 | $0.60 | — | 100% | 296 ms | 75 tok/s | Normal | |
| Parasail | fp4 | 131K | 118K | $0.10 | $0.75 | $0.055 | 100% | 352 ms | 164 tok/s | Normal | |
| Mara | — | 131K | 118K | $0.15 | $0.75 | — | 100% | 743 ms | 146 tok/s | Normal | |
| SambaNova | — | 131K | 118K | $0.14 | $0.95 | — | 100% | 941 ms | 326 tok/s | Normal | |
| Cerebras | fp16 | 131K | 41K | $0.35 | $0.75 | $0.35 | 100% | 165 ms | 733 tok/s | Normal | |
| DeepInfra | fp8 | 131K | 118K | $0.20 | $0.95 | — | 88.9% | 1.44 s | 61 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#45
by tokens, Oct 29, 2026
67.2B
tokens that day · 7 days −39%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- OpenAI
GPT-6 Luna
- Input
- $0.10
- Output
- $0.50
- Context
- 1.05M
- OpenAI
GPT-6.1 Sol
- Input
- $2.00
- Output
- $10.00
- Context
- 1.05M
- OpenAI
GPT-5.6 Luna
- Input
- $0.20
- Output
- $1.20
- Context
- 1.05M
- OpenAI
GPT-6.1 Terra
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M
- OpenAI
GPT-6 Luna Pro
- Input
- $0.10
- Output
- $0.50
- Context
- 1.05M
- OpenAI
GPT-6 Astra
- Input
- $10.00
- Output
- $50.00
- Context
- 1.05M