LLM API pricing
gpt-oss-120b vs Gemma 4 31B: price per 1M tokens
Updated 2026-10-14
gpt-oss-120b costs $0.15 / $0.6 per 1M input/output tokens (Amazon Bedrock (regional)) vs $0.14 / $0.4 for Gemma 4 31B (Amazon Bedrock (regional)). Blended 3:1, gpt-oss-120b is +28% vs Gemma 4 31B.
gpt-oss-120b by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Amazon Bedrock (regional) | $0.15 | $0.6 | n/a | AWS credits |
Gemma 4 31B by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Amazon Bedrock (regional) | $0.14 | $0.4 | n/a | AWS credits |
Worked examples (monthly bill at list price)
| Workload | gpt-oss-120b | Gemma 4 31B | Difference |
|---|---|---|---|
| Support chatbot: 100,000 × 1,000 in / 300 out | $33.00 | $26.00 | +27% |
| RAG over docs: 50,000 × 4,000 in / 500 out | $45.00 | $38.00 | +18% |
| Coding agent: 200,000 × 20,000 in / 2,000 out | $840.00 | $720.00 | +17% |
Tokens per $25,000 of credits
- gpt-oss-120b via Amazon Bedrock (regional) (AWS credits): 95.24B tokens
- Gemma 4 31B via Amazon Bedrock (regional) (AWS credits): 121.95B tokens
More
Cost calculator
Monthly bill: $33
Paid with AWS credits: 757.6 months of runway.
Related cost calculators
- Amazon Bedrock AgentCore Pricing Calculator · Runtime, Gateway, Memory & Policy Costs
- Bedrock Pricing Calculator · AI Model & Tool Cost Estimator
- Amazon SageMaker AI Pricing Calculator · On-Demand Studio, Training & Inference
Prices and credit amounts are estimates and may change. Check AWS for current terms.