Dekallm pricing overview
TokenWatch tracks 11 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: Mistral Nemo at $0.018 per million input tokens and $0.030 per million output tokens. 8 of 11 text models publish a cache-read price; 11 carry a zero-data-retention tag.
Dekallm text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| mistral | dekallm | Mistral: Mistral Nemo | $0.018 | $0.030 | — | $0.018 |
| openai | dekallm | OpenAI: gpt-oss-20b | $0.029 | $0.140 | $0.029 | $0.030 |
| openai | dekallm | OpenAI: gpt-oss-120b | $0.030 | $0.180 | $0.030 | $0.031 |
| qwen | dekallm | Qwen: Qwen3.8 27B | $0.040 | $2.50 | $0.020 | $0.033 |
| dekallm | Google: Gemma 4 26B A4B | $0.060 | $0.330 | $0.040 | $0.042 | |
| dekallm | Google: Gemma 4 31B | $0.140 | $0.400 | $0.050 | $0.054 | |
| qwen | dekallm | Qwen: Qwen3.6 35B A3B | $0.100 | $1.00 | $0.050 | $0.056 |
| nvidia | dekallm | NVIDIA: Nemotron 3 Super | $0.080 | $0.450 | — | $0.082 |
| qwen | dekallm | Qwen: Qwen3 30B A3B Instruct 2507 | $0.090 | $0.300 | — | $0.091 |
| z-ai | dekallm | Z.ai: GLM 5.3 | $0.250 | $2.95 | $0.180 | $0.196 |
| deepseek | dekallm | DeepSeek: DeepSeek V4 Pro 0813 | $1.08 | $3.80 | $0.180 | $0.221 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.