DekaLLM
Inference provider
- Endpoints
- 10
- Models
- 10
Models served
10 shown
| Model | Creator | Type | In $/1M | Out $/1M | Context | Max output | Tools | Region |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-20260813 | DeepSeek | Chat | $0.88 | $3.80 | 1.05M | 944K | Region not stated | |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it-20260403 | Chat | $0.06 | $0.33 | 262K | 236K | Region not stated | ||
| GLM-5.3 z-ai/glm-5.3-20260816 | Z.ai (Zhipu AI) | Chat | $0.180.13× median | $2.95 | 1.05M | 944K | Region not stated | |
| GPT OSS 20B openai/gpt-oss-20b | OpenAI | Chat | $0.029 | $0.14 | 131K | 118K | Region not stated | |
| GPT-OSS 120B openai/gpt-oss-120b | OpenAI | Chat | $0.03 | $0.18 | 131K | 118K | Region not stated | |
| Mistral Nemo mistralai/mistral-nemo | Mistral AI | Chat | $0.018 | $0.03 | 131K | 105K | Region not stated | |
| Nemotron 3 Super 120B nvidia/nemotron-3-super-120b-a12b-20230311 | NVIDIA | Chat | $0.08 | $0.45 | 262K | 236K | Region not stated | |
| Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 | Alibaba (Qwen) | Chat | $0.09 | $0.30 | 262K | 236K | Region not stated | |
| Qwen3.6 35B-A3B qwen/qwen3.6-35b-a3b-20260415 | Alibaba (Qwen) | Chat | $0.10 | $1.00 | 262K | 236K | Region not stated | |
| Qwen3.8-27B qwen/qwen3.8-27b-20260814 | Alibaba (Qwen) | Chat | $0.040.09× median | $2.50 | 262K | 236K | Region not stated |
One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.