Amazon Bedrock: Models and Prices
Inference provider serving open-weight models.
Amazon Bedrock served 65B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #43 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| Kimi K3 | Kimi | 1.8% | 35B | $3.00 | $15.00 | 63 | 98.7% | 1.05M |
| gpt-oss-20b | gpt-oss | 12.0% | 25B | $0.07 | $0.15 | - | 100.0% | 131K |
| gpt-oss-120b | gpt-oss | 1.4% | 6B | $0.15 | $0.60 | 145 | 100.0% | 131K |
| GLM 5 | GLM | - | - | $1.00 | $3.20 | 118 | 100.0% | 203K |
| Kimi K2.5 | Kimi | - | - | $0.60 | $3.00 | 86 | 99.9% | 262K |
| Qwen3 Coder 30B A3B Instruct | Qwen | - | - | $0.15 | $0.60 | - | - | – |
| Llama 3.1 70B Instruct | Llama | - | - | $0.72 | $0.72 | 66 | 100.0% | 131K |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Headquarters
- United States
- Status page
- health.aws.amazon.com/health/status
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com