Mancer 2

Inference host · 6 models · 6 priced routes

Models on Mancer 2

Model	In / out per 1M	Vs headline
gpt-oss-120b fp8 · 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.	$0.045 / $0.275+512% vs headline	+512%	fp8 · 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.
DeepSeek V4 Flash 0731 fp8 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.175 / $0.5+187% vs headline	+187%	fp8 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
DeepSeek V4 Flash 0423 fp8 · DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.	$0.175 / $0.5+128% vs headline	+128%	fp8 · DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
DeepSeek V4.1 Flash fp8 · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.15 / $0.75+176% vs headline	+176%	fp8 · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
Qwen3.8 27B fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.175 / $2.5-21% vs headline	-21%	fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 4.7 fp4 · GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.	$0.7 / $2.5+95% vs headline	+95%	fp4 · GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.