Phala

Inference host · 18 models · 19 priced routes

Models on Phala

Model	In / out per 1M	Vs headline
Qwen2.5 7B Instruct Qwen2.5 7B is the latest series of Qwen large language models.	$0.1 / $0.2Same vs headline	Same	Qwen2.5 7B is the latest series of Qwen large language models.
GLM 5.3 Flash nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.15 / $0.5+389% vs headline	+389%	nvfp4 · GLM-5.3-Flash is a native multimodal model from Z.ai.
gpt-oss-120b 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.	$0.15 / $0.6+1467% vs headline	+1467%	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 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.	$0.2 / $1.2+71% vs headline	+71%	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.
Qwen3.6 35B A3B Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.	$0.2 / $1.27+874% vs headline	+874%	Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
DeepSeek V4.1 Flash 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 / $1.2+383% vs headline	+383%	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 0731 DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.44 / $1.32+639% vs headline	+639%	DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
Qwen3.8 27B Qwen3.8 27B is an open-weight dense vision-language model from Qwen.	$0.2 / $2.5-19% vs headline	-19%	Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
Qwen3.5-27B The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.	$0.3 / $2.4+54% vs headline	+54%	The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.
Qwen3.6 27B Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.	$0.32 / $2.7-10% vs headline	-10%	Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
DeepSeek V3.2 DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.	$1 / $1+245% vs headline	+245%	DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
Qwen3.5 397B A17B The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.	$0.55 / $3.5+47% vs headline	+47%	The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.
GLM 5.1 GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.	$1.21 / $4.2+40% vs headline	+40%	GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.
Kimi K2.6 Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.	$1.09 / $4.6+15% vs headline	+15%	Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
GLM 5.3 GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$1.4 / $4.4+344% vs headline	+344%	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 DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$1.45 / $4.36+120% vs headline	+120%	DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
Kimi K3.1 Pro us · 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%	us · 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 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%	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 Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$3 / $15Same vs headline	Same	Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.