gpt-oss-20b
openai/gpt-oss-20b
- context
- 131K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Providers
- AkashMLView AkashML
- Amazon BedrockView Amazon Bedrock
- CoreWeaveView CoreWeave
- DarkbloomView Darkbloom
- DeepInfraView DeepInfra
- DekaLLMView DekaLLM
- GoogleView Google
- GroqView Groq
- NovitaView Novita
- ParasailView Parasail
- PrimeIntellectView PrimeIntellect
- SiliconFlowView SiliconFlow
- TogetherView Together
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| AkashML | $0.02 | $0.10 |
| Amazon Bedrockamazon-bedrock | $0.07 | $0.15 |
| Amazon Bedrockamazon-bedrock/eu-west-1 | $0.07 | $0.15 |
| CoreWeave | $0.03 | $0.13 |
| Darkbloom | $0.018 | $0.09 |
| DeepInfra | $0.03 | $0.14 |
| DekaLLM | $0.029 | $0.14 |
| $0.07 | $0.25 | |
| Groq | $0.075 | $0.30 |
| Novita | $0.04 | $0.15 |
| Parasail | $0.03 | $0.15 |
| PrimeIntellect | $0.07 | $0.30 |
| SiliconFlow | $0.04 | $0.18 |
| Together | $0.05 | $0.20 |
AkashML
- input / 1M
- $0.02
- output / 1M
- $0.10
Amazon Bedrock
amazon-bedrock
- input / 1M
- $0.07
- output / 1M
- $0.15
Amazon Bedrock
amazon-bedrock/eu-west-1
- input / 1M
- $0.07
- output / 1M
- $0.15
CoreWeave
- input / 1M
- $0.03
- output / 1M
- $0.13
Darkbloom
- input / 1M
- $0.018
- output / 1M
- $0.09
DeepInfra
- input / 1M
- $0.03
- output / 1M
- $0.14
DekaLLM
- input / 1M
- $0.029
- output / 1M
- $0.14
Google
- input / 1M
- $0.07
- output / 1M
- $0.25
Groq
- input / 1M
- $0.075
- output / 1M
- $0.30
Novita
- input / 1M
- $0.04
- output / 1M
- $0.15
Parasail
- input / 1M
- $0.03
- output / 1M
- $0.15
PrimeIntellect
- input / 1M
- $0.07
- output / 1M
- $0.30
SiliconFlow
- input / 1M
- $0.04
- output / 1M
- $0.18
Together
- input / 1M
- $0.05
- output / 1M
- $0.20
Use this model
through Nautili
Route requests to gpt-oss-20b 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.