InferenceNet

Inference host · 6 models · 16 priced routes

Models on InferenceNet

Model	In / out per 1M	Vs headline
GLM 5.3 Flash fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.045 / $0.14+41% vs headline	+41%	fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
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.	$0.045 / $0.3Same vs headline	Same	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.
GLM 5.3 Flash us, fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.108 / $0.35+247% vs headline	+247%	us, fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
DeepSeek V4.1 Flash 1017 fp8 · 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.	$0.08 / $0.55-25% vs headline	-25%	fp8 · 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.
DeepSeek V4.1 Flash 1017 us, fp8 · 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.	$0.08 / $0.55-25% vs headline	-25%	us, fp8 · 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.
DeepSeek V4.1 Flash us, 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.	$0.103 / $0.6+109% vs headline	+109%	us, 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.
GLM 5.3 us, fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.08 / $3.6+98% vs headline	+98%	us, fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
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.	$0.684 / $3.6+192% vs headline	+192%	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 us, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$0.239 / $10.8-52% vs headline	-52%	us, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3.1 Pro mxfp4 · 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 / $9+59% vs headline	+59%	mxfp4 · 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.
Kimi K3.1 Pro mxfp4-us, mxfp4 · 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 / $9+59% vs headline	+59%	mxfp4-us, mxfp4 · 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.
Kimi K3 fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$1.3 / $11.4-36% vs headline	-36%	fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 us-fast, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$2.24 / $14.5-12% vs headline	-12%	us-fast, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3.1 Pro us-fast, mxfp4 · 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.	$2.7 / $13.5+138% vs headline	+138%	us-fast, mxfp4 · 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.
Kimi K3.1 Pro fast, mxfp4 · 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.	$2.7 / $13.5+138% vs headline	+138%	fast, mxfp4 · 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.
Kimi K3 fast, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$3.25 / $16+7% vs headline	+7%	fast, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.