Wafer

Inference host · 11 models · 21 priced routes

Models on Wafer

Model	In / out per 1M	Vs headline
GLM 5.3 Flash us, nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.048 / $0.2+77% vs headline	+77%	us, nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
DeepSeek V4 Flash 0731 us, nvfp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.043 / $0.3+21% vs headline	+21%	us, nvfp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
DeepSeek V4 Flash 0731 fast, nvfp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.08 / $0.35+65% vs headline	+65%	fast, nvfp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
DeepSeek V4.1 Flash 1017 us, mxfp4 · 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.	$0.038 / $0.5-42% vs headline	-42%	us, mxfp4 · 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, mxfp4 · 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 / $0.5+46% vs headline	+46%	us, mxfp4 · 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 nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.12 / $0.5+342% vs headline	+342%	nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
DeepSeek V4.1 Flash mxfp4 · 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.	$0.1 / $0.65+118% vs headline	+118%	mxfp4 · 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.
DeepSeek V4.1 Flash 1017 mxfp4 · 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.	$0.16 / $0.5-7% vs headline	-7%	mxfp4 · 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.
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.	$0.179 / $1.4Same vs headline	Same	fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
DeepSeek V4 Flash 0423 mxfp4 · 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.	$0.7 / $0.17+404% vs headline	+404%	mxfp4 · 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 Pro 0813 us, mxfp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$0.115 / $4.6+25% vs headline	+25%	us, mxfp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
DeepSeek V4 Pro 0813 mxfp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$0.285 / $4.3+30% vs headline	+30%	mxfp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
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.	$1.4 / $1.4+189% vs headline	+189%	us, fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Qwen3.8 27B fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.2 / $6+73% vs headline	+73%	fp8 · Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 5.2 us, fp4 · GLM 5.2 is a large-scale reasoning model from Z.ai.	$0.034 / $7+91% vs headline	+91%	us, fp4 · GLM 5.2 is a large-scale reasoning model from Z.ai.
GLM 5.2 fp4 · GLM 5.2 is a large-scale reasoning model from Z.ai.	$1.4 / $4.4+131% vs headline	+131%	fp4 · GLM 5.2 is a large-scale reasoning model from Z.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 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.	$2 / $10+76% vs headline	+76%	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 mxfp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$1.99 / $15-13% vs headline	-13%	mxfp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 fast, mxfp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$0.5 / $22-2% vs headline	-2%	fast, mxfp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.