Sail Research

Inference host · 8 models · 15 priced routes

Models on Sail Research

Model	In / out per 1M	Vs headline
DeepSeek V4 Flash 0731 us, fp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.019 / $0.3Same vs headline	Same	us, fp4 · 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 fp4 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.021 / $0.3+2% vs headline	+2%	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-us, 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.	$0.101 / $0.15-57% vs headline	-57%	fp4-us, 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.
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.	$0.06 / $0.4+766% vs headline	+766%	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.
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.	$0.152 / $0.225-35% vs headline	-35%	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.
GLM 5.3 Flash us, fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.175 / $0.625+492% vs headline	+492%	us, fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
GLM 5.3 Flash fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.175 / $0.625+492% vs headline	+492%	fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
GLM 5.3 fp8 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.77 / $4+226% vs headline	+226%	fp8 · 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 us, fp8 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$0.77 / $4+226% vs headline	+226%	us, fp8 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
DeepSeek V4 Pro 0813 us, fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$1.35 / $2.4+63% vs headline	+63%	us, fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
DeepSeek V4 Pro 0813 fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$1.35 / $2.4+63% vs headline	+63%	fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
Kimi K3 fp4-us, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$1.2 / $9-47% vs headline	-47%	fp4-us, fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3 fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$0.885 / $10.5-45% vs headline	-45%	fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Kimi K3.1 Pro fp4-us, 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.	$0.346 / $16.6+94% vs headline	+94%	fp4-us, 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 K3.1 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.	$0.346 / $16.6+94% vs headline	+94%	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.