# OpenAI: gpt-oss-120b

- Model id: `openai/gpt-oss-120b`
- Served by: -
- List price per 1M tokens, input / output, from: -, with 0% platform fee. A request is billed at the list price of the host that served it.
- Context: 131K, max output 118K
- Prices read 2026-11-15 09:33 UTC
- Page: https://plaingateway.com/models/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...

## Hosts

| Host | Endpoint | In / out /M | Cache read /M | Context | Served |
|---|---|---|---|---|---|
| Primeintellect | `primeintellect/fp4` | $0.035 / $0.076 | $0.032 | 131K | no |
| Near Ai | `near-ai/fp4` | $0.03 / $0.15 | $0.015 | 131K | no |
| Venice | `venice/int4` | $0.03 / $0.15 | $0.03 | 128K | no |
| Coreweave | `coreweave/fp4` | $0.03 / $0.17 | $0.03 | 131K | no |
| Dekallm | `dekallm/bf16` | $0.03 / $0.18 | $0.03 | 131K | no |
| Akashml | `akashml/fp4` | $0.03 / $0.187 | $0.03 | 131K | no |
| DeepInfra | `deepinfra/bf16` | $0.037 / $0.17 | - | 131K | no |
| Crusoe | `crusoe/bf16` | $0.05 / $0.25 | $0.05 | 131K | no |
| Mancer | `mancer/fp8` | $0.07 / $0.25 | $0.07 | 131K | no |
| Sail Research | `sail-research/fp4` | $0.06 / $0.40 | $0.03 | 131K | no |
| Digitalocean | `digitalocean` | $0.06 / $0.42 | $0.012 | 128K | no |
| Google Vertex | `google-vertex/global` | $0.09 / $0.36 | - | 131K | no |
| Baseten | `baseten/fp4` | $0.10 / $0.50 | $0.10 | 128K | no |
| Baseten | `baseten/fp4/us` | $0.10 / $0.50 | $0.10 | 128K | no |
| Amazon Bedrock | `amazon-bedrock` | $0.15 / $0.60 | - | 131K | no |
| Amazon Bedrock | `amazon-bedrock/eu-west-1` | $0.15 / $0.60 | - | 131K | no |
| Groq | `groq` | $0.15 / $0.60 | $0.075 | 131K | no |
| Nebius | `nebius/fp4` | $0.15 / $0.60 | $0.10 | 131K | no |
| Siliconflow | `siliconflow/fp8` | $0.15 / $0.60 | $0.075 | 131K | no |
| Together | `together` | $0.15 / $0.60 | - | 131K | no |
| Parasail | `parasail/fp4` | $0.10 / $0.75 | $0.055 | 131K | no |
| Io Net | `io-net/fp4` | $0.25 / $0.45 | $0.085 | 131K | no |
| Parasail | `parasail/fast` | $0.15 / $0.75 | - | 131K | no |
| Sambanova | `sambanova` | $0.14 / $0.95 | - | 131K | no |
| DeepInfra | `deepinfra/fp8` | $0.20 / $0.95 | - | 131K | no |
| Cerebras | `cerebras/fp16` | $0.35 / $0.75 | $0.35 | 131K | no |

## First request

```sh
curl https://api.plaingateway.com/api/v1/chat/completions \
  -H "Authorization: Bearer $PLAINGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-oss-120b", "messages": [{"role": "user", "content": "Say hello in five words."}]}'
```

Sign up at https://plaingateway.com/signup (no card), create a key, send a test call, and add credits when you want more. New accounts may get a small starting credit. The whole bootstrap for agents: https://plaingateway.com/llms.txt