gpt-oss-120b
openai/gpt-oss-120b
- context
- 131K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
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...
Providers
- AkashMLView AkashML
- Amazon BedrockView Amazon Bedrock
- BaseTenView BaseTen
- CerebrasView Cerebras
- CoreWeaveView CoreWeave
- CrusoeView Crusoe
- DeepInfraView DeepInfra
- DekaLLMView DekaLLM
- DigitalOceanView DigitalOcean
- GoogleView Google
- GroqView Groq
- Mancer 2View Mancer 2
- MaraView Mara
- NebiusView Nebius
- NovitaView Novita
- ParasailView Parasail
- PhalaView Phala
- SambaNovaView SambaNova
- SiliconFlowView SiliconFlow
- TogetherView Together
- VeniceView Venice
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| AkashML | $0.03 | $0.187 |
| Amazon Bedrockamazon-bedrock | $0.15 | $0.60 |
| Amazon Bedrockamazon-bedrock/eu-west-1 | $0.15 | $0.60 |
| BaseTen | $0.10 | $0.50 |
| Cerebras | $0.35 | $0.75 |
| CoreWeave | $0.03 | $0.17 |
| Crusoe | $0.05 | $0.25 |
| DeepInfradeepinfra/bf16 · bf16 | $0.037 | $0.17 |
| DeepInfradeepinfra/fp8 · fp8 | $0.20 | $0.95 |
| DeepInfradeepinfra/turbo · bf16 | $0.15 | $0.60 |
| DekaLLM | $0.03 | $0.18 |
| DigitalOcean | $0.06 | $0.42 |
| $0.09 | $0.36 | |
| Groq | $0.15 | $0.60 |
| Mancer 2 | $0.05 | $0.25 |
| Mara | $0.15 | $0.75 |
| Nebius | $0.15 | $0.60 |
| Novita | $0.05 | $0.25 |
| Parasail | $0.10 | $0.75 |
| Phala | $0.15 | $0.60 |
| SambaNova | $0.14 | $0.95 |
| SiliconFlow | $0.15 | $0.60 |
| Together | $0.15 | $0.60 |
| Venice | $0.03 | $0.15 |
AkashML
- input / 1M
- $0.03
- output / 1M
- $0.187
Amazon Bedrock
amazon-bedrock
- input / 1M
- $0.15
- output / 1M
- $0.60
Amazon Bedrock
amazon-bedrock/eu-west-1
- input / 1M
- $0.15
- output / 1M
- $0.60
BaseTen
- input / 1M
- $0.10
- output / 1M
- $0.50
Cerebras
- input / 1M
- $0.35
- output / 1M
- $0.75
CoreWeave
- input / 1M
- $0.03
- output / 1M
- $0.17
Crusoe
- input / 1M
- $0.05
- output / 1M
- $0.25
DeepInfra
deepinfra/bf16 · bf16
- input / 1M
- $0.037
- output / 1M
- $0.17
DeepInfra
deepinfra/fp8 · fp8
- input / 1M
- $0.20
- output / 1M
- $0.95
DeepInfra
deepinfra/turbo · bf16
- input / 1M
- $0.15
- output / 1M
- $0.60
DekaLLM
- input / 1M
- $0.03
- output / 1M
- $0.18
DigitalOcean
- input / 1M
- $0.06
- output / 1M
- $0.42
Google
- input / 1M
- $0.09
- output / 1M
- $0.36
Groq
- input / 1M
- $0.15
- output / 1M
- $0.60
Mancer 2
- input / 1M
- $0.05
- output / 1M
- $0.25
Mara
- input / 1M
- $0.15
- output / 1M
- $0.75
Nebius
- input / 1M
- $0.15
- output / 1M
- $0.60
Novita
- input / 1M
- $0.05
- output / 1M
- $0.25
Parasail
- input / 1M
- $0.10
- output / 1M
- $0.75
Phala
- input / 1M
- $0.15
- output / 1M
- $0.60
SambaNova
- input / 1M
- $0.14
- output / 1M
- $0.95
SiliconFlow
- input / 1M
- $0.15
- output / 1M
- $0.60
Together
- input / 1M
- $0.15
- output / 1M
- $0.60
Venice
- input / 1M
- $0.03
- output / 1M
- $0.15
Use this model
through Nautili
Route requests to gpt-oss-120b through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.