Relace

Inference host · 11 models · 13 priced routes

Models on Relace

Model	In / out per 1M	Vs headline
GLM 5.3 Flash fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.012 / $0.158Same vs headline	Same	fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
DeepSeek V4 Flash 0731 fp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.03 / $0.32+15% vs headline	+15%	fp4 · 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 fp4 · 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.	$0.035 / $0.5-42% vs headline	-42%	fp4 · 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 fp4 · 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.	$0.035 / $0.5+39% vs headline	+39%	fp4 · 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 Flash 0423 fp4 · 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.	$0.03 / $1.28+204% vs headline	+204%	fp4 · 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 1017 fast, fp4 · 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.	$0.3 / $0.9+71% vs headline	+71%	fast, fp4 · 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 fast, fp4 · 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.	$0.3 / $0.9+314% vs headline	+314%	fast, fp4 · 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 Pro 0423 fp4 · DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.	$0.9 / $1.5Same vs headline	Same	fp4 · DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
DeepSeek V4 Pro 0813 fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$0.227 / $3.78+13% vs headline	+13%	fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
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.	$0.07 / $4.38+137% vs headline	+137%	fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
GLM 5.2 fp4 · GLM 5.2 is a large-scale reasoning model from Z.ai.	$0.0065 / $7.91+113% vs headline	+113%	fp4 · GLM 5.2 is a large-scale reasoning model from Z.ai.
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.	$0.377 / $7.95Same vs headline	Same	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.
Kimi K3 fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$1.8 / $11.2-31% vs headline	-31%	fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.