gpt-oss-20b
OpenAI · Active · available in 13 of 31 regions
Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
- Context window
- —
- Max output
- —
- Input / 1M
- $0.070
- us-east-1
- Output / 1M
- $0.300
What gpt-oss-20b is good for
editorialgpt-oss-20b, and is the cheapest option from this provider at $0.070 per 1M input tokens. Callable in 13 of 31 regions.
Suits
- Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.
- Cost. The cheapest OpenAI model here at $0.070 per 1M input tokens — the default choice for high-volume, low-difficulty work.
Think twice if
- Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
- Function calling. No tool use, so it cannot drive an agent loop or call your APIs — it answers from what is in the prompt.
- Documents with layout. Text only. Scanned PDFs, screenshots and charts need a vision model or an OCR step first.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Chat and assistants
Conversational work where responsiveness matters as much as depth.
- · A customer-facing assistant where the first token needs to appear in under a second.
- · An in-product copilot that explains what the user is looking at and answers follow-ups.
- · A triage bot that qualifies an incoming request before routing it to the right team.
Coding
Writing, reviewing and refactoring code, usually across more than one file.
- · A review pass that flags real defects with a severity and leaves style alone.
- · A framework upgrade applied across a repository, one module at a time, tests green between each.
- · Turning a failing bug report into a reproducing test and then a fix.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $0.070 | $0.300 | — | — | $0.035 | $0.150 | API |
| us-east-2 US East (Ohio) | $0.070 | $0.300 | — | — | $0.035 | $0.150 | API |
| us-west-2 US West (Oregon) | $0.070 | $0.300 | — | — | $0.035 | $0.150 | API |
| eu-west-1 EU (Ireland) | $0.080 | $0.350 | — | — | $0.040 | $0.180 | API |
| eu-west-2 EU (London) | $0.110 | $0.470 | — | — | $0.050 | $0.230 | API |
| eu-central-1 EU (Frankfurt) | $0.090 | $0.400 | — | — | $0.050 | $0.200 | API |
| eu-north-1 EU (Stockholm) | $0.070 | $0.300 | — | — | $0.035 | $0.150 | API |
| eu-south-1 EU (Milan) | $0.090 | $0.400 | — | — | $0.050 | $0.200 | API |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.080 | $0.360 | — | — | $0.040 | $0.180 | API |
| ap-south-1 Asia Pacific (Mumbai) | $0.080 | $0.350 | — | — | $0.040 | $0.180 | API |
| ap-southeast-2 Asia Pacific (Sydney) | $0.072 | $0.309 | — | — | $0.036 | $0.154 | API |
| ap-southeast-3 Asia Pacific (Jakarta) | $0.070 | $0.310 | — | — | $0.040 | $0.160 | API |
| sa-east-1 South America (Sao Paulo) | $0.080 | $0.360 | — | — | $0.040 | $0.180 | API |
Region availability
On-demand us-east-1 On-demand On-demand us-east-2 On-demand Not available us-west-1 Not available On-demand us-west-2 On-demand Not available ca-central-1 Not available Not available ca-west-1 Not available Not available mx-central-1 Not available On-demand eu-west-1 On-demand On-demand eu-west-2 On-demand Not available eu-west-3 Not available On-demand eu-central-1 On-demand Not available eu-central-2 Not available On-demand eu-north-1 On-demand On-demand eu-south-1 On-demand Not available eu-south-2 Not available Not available ap-east-2 Not available On-demand ap-northeast-1 On-demand Not available ap-northeast-2 Not available Not available ap-northeast-3 Not available On-demand ap-south-1 On-demand Not available ap-south-2 Not available Not available ap-southeast-1 Not available On-demand ap-southeast-2 On-demand On-demand ap-southeast-3 On-demand Not available ap-southeast-4 Not available Not available ap-southeast-5 Not available Not available ap-southeast-6 Not available Not available ap-southeast-7 Not available Not available il-central-1 Not available Not available af-south-1 Not available On-demand sa-east-1 On-demand
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, gpt-oss-20b can be served without the request leaving 12 of the 25 jurisdictions with a Bedrock region.
gpt-oss-20b appears in
Common questions
- How much does gpt-oss-20b cost on Amazon Bedrock?
- $0.070 per 1M input tokens and $0.300 per 1M output tokens in us-east-1.
- Which AWS regions support gpt-oss-20b?
- 13 of 31 regions: us-east-1, us-east-2, us-west-2, eu-west-1, eu-west-2, eu-central-1, eu-north-1, eu-south-1, ap-northeast-1, ap-south-1, ap-southeast-2, ap-southeast-3, sa-east-1.
- What is the model ID for gpt-oss-20b on Bedrock?
- openai.gpt-oss-20b-1:0.