DekaLLM: Models and Prices
Inference API hosted entirely in Indonesia, offered through Lintasarta Cloudeka.
DekaLLM served 164B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #32 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| Qwen3.8 27B | Qwen | 8.1% | 47B | $0.049 | $3.00 | 140 | 99.8% | 262K |
| Gemma 4 26B A4B | Gemma | 10.7% | 28B | $0.06 | $0.33 | 62 | 100.0% | 262K |
| gpt-oss-120b | gpt-oss | 6.4% | 27B | $0.03 | $0.18 | 40 | 99.9% | 131K |
| DeepSeek V4.1 Flash | DeepSeek | <0.1% | 18B | $0.12 | $1.20 | 78 | 99.4% | 1.05M |
| GLM 5.3 Flash | GLM | 0.1% | 14B | $0.10 | $1.00 | 105 | 97.2% | 1.05M |
| Mistral Nemo | Mistral | 5.2% | 13B | $0.018 | $0.03 | 19 | 100.0% | 131K |
| gpt-oss-20b | gpt-oss | 4.0% | 8B | $0.029 | $0.14 | 20 | 99.5% | 131K |
| Nemotron 3 Super | Nemotron | 1.1% | 6B | $0.08 | $0.45 | 21 | 99.5% | 262K |
| Qwen3.6 35B A3B | Qwen | 5.4% | 2B | $0.10 | $1.00 | 95 | 99.2% | 262K |
| Qwen3 30B A3B Instruct 2507 | Qwen | 0.5% | 113M | $0.09 | $0.30 | 84 | 99.5% | 262K |
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
- Website
- cloudeka.id
- Headquarters
- Indonesia
Sources: Cloudeka.
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