DekaLLM

Inference host · 11 models · 11 priced routes

Models on DekaLLM

Model	In / out per 1M	Vs headline
Mistral Nemo fp8 · A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.	$0.018 / $0.03Same vs headline	Same	fp8 · A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
gpt-oss-20b bf16 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.	$0.029 / $0.14+683% vs headline	+683%	bf16 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
gpt-oss-120b bf16 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.	$0.03 / $0.18+303% vs headline	+303%	bf16 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
Gemma 4 26B A4B bf16 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.	$0.06 / $0.33+50% vs headline	+50%	bf16 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Qwen3 30B A3B Instruct 2507 Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.	$0.09 / $0.3Same vs headline	Same	Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.
Nemotron 3 Super fp8 · NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.	$0.08 / $0.45+10% vs headline	+10%	fp8 · NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.
Gemma 4 31B Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.	$0.14 / $0.4+28% vs headline	+28%	Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.18 / $0.68+16% vs headline	+16%	DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
Qwen3.6 35B A3B Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.	$0.1 / $1+577% vs headline	+577%	Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
Qwen3.8 27B Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.04 / $2.5-32% vs headline	-32%	Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 5.3 GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.18 / $2.95+80% vs headline	+80%	GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.