GPT OSS 20B 1 API Pricing
As of October 10, 2026, GPT OSS 20B 1 costs $0.07 per 1M input tokens and $0.30 per 1M output tokens on Amazon Bedrock. It has a 128,000-token context window and returns up to 16,384 tokens per response.
- Input
- $0.07 / 1M tokens
- Output
- $0.30 / 1M tokens
- Context window
- 128,000 tokens
- Max output
- 16,384 tokens
- Providers
- 1
- Added to LiteLLM
- August 2025
GPT OSS 20B 1 pricing by provider
4 listings across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Amazon Bedrock | openai.gpt-oss-20b-1:0 | $0.07 | $0.30 | 128K |
| Amazon Bedrockus-gov-east-1 | bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0 | $0.084 | $0.36 | 128K |
| Amazon Bedrockus-gov-west-1 | bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0 | $0.084 | $0.36 | 128K |
| Amazon BedrockUS GovCloud cross-region | us-gov.openai.gpt-oss-20b-1:0 | $0.084 | $0.36 | 128K |
What GPT OSS 20B 1 costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Amazon Bedrock | $0.29 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Amazon Bedrock | $0.76 |
GPT OSS 20B 1 features
- Function calling
- Structured output
- Reasoning
Use GPT OSS 20B 1 with LiteLLM
Call GPT OSS 20B 1 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="openai.gpt-oss-20b-1:0",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-oss-20b-1
litellm_params:
model: openai.gpt-oss-20b-1:0
aws_region_name: os.environ/AWS_REGION_NAMEcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-oss-20b-1",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT OSS 20B 1 FAQ
How much does GPT OSS 20B 1 cost?
GPT OSS 20B 1 costs $0.07 per 1M input tokens and $0.30 per 1M output tokens on Amazon Bedrock.
What is the context window of GPT OSS 20B 1?
GPT OSS 20B 1 has a 128,000-token context window and returns up to 16,384 tokens per response.
Which providers offer GPT OSS 20B 1?
GPT OSS 20B 1 is available from Amazon Bedrock through LiteLLM, using the model name openai.gpt-oss-20b-1:0.
How do I call GPT OSS 20B 1 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="openai.gpt-oss-20b-1:0", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT OSS 20B 1 support?
GPT OSS 20B 1 supports function calling, structured output and reasoning.
When did LiteLLM add GPT OSS 20B 1?
GPT OSS 20B 1 was added to LiteLLM's model price file in August 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Amazon Bedrock.
Provider pages: Amazon Bedrock.
