AkashML

Inference host · 8 models · 8 priced routes

Models on AkashML

Model	In / out per 1M	Vs headline
gpt-oss-20b fp4 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.	$0.02 / $0.1+452% vs headline	+452%	fp4 · gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
gpt-oss-120b fp4 · 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 / $0.187+313% vs headline	+313%	fp4 · 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 fp4 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.	$0.07 / $0.24+32% vs headline	+32%	fp4 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Llama 3.3 70B Instruct fp8 · The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).	$0.2 / $0.52+81% vs headline	+81%	fp8 · The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
Qwen3.6 35B A3B fp8 · 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 / $0.9+525% vs headline	+525%	fp8 · 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 fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.225 / $1.98-31% vs headline	-31%	fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 5.3 fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.19 / $4.4+157% vs headline	+157%	fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Kimi K3.1 Pro fp4 · Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.	$1.8 / $10+70% vs headline	+70%	fp4 · Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.