Inference provider
Explore models served by Phala AI. Compare capabilities, context, privacy, and pricing across its available routes.
In this catalog
Across the catalog
Per 1M text tokens
Tokens per request
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
GLM-5.2 is Z.ai's open-weight Mixture-of-Experts model for long-horizon tasks and software engineering. It takes text input and output with a 1M-token context window and up to 128K output tokens, and offers multiple thinking effort levels to balance performance and latency.
Gemma 4 26B A4B Uncensored is a community fine-tune of Google DeepMind's Gemma 4 26B A4B, modified to reduce refusals. The base model is a Mixture-of-Experts model with 25.2B total and 3.8B active parameters; this variant takes text input and produces text output.
Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.
DeepSeek-V3.2 uses DeepSeek Sparse Attention for efficient long contexts, with strong reasoning and tool use.
DeepSeek V4 Flash 0731 is the July 31, 2026 official release of DeepSeek V4 Flash, a Mixture-of-Experts model with 284B total and 13B active parameters and a 1M-token context window. It keeps the preview's architecture and size but is re-post-trained for much stronger agentic performance, with low, high and max reasoning effort.
Moonshot AI's open-weight multimodal agentic model has 1T total and 32B active parameters, built for long-horizon coding and tool use.
Qwen3.5-397B-A17B is a multimodal Mixture-of-Experts model from Alibaba's Qwen team, with 397B total parameters and 17B active per token. It takes text, image and video input and produces text, with a 262K-token native context window (extendable to about 1M), a default thinking mode, tool calling and support for 201 languages and dialects.
Qwen's dense 27B vision-language model supports reasoning, coding and tool-driven tasks.
HauhauCS's Aggressive adaptation of Qwen3.8-27B retains text and visual capabilities while modifying refusal behavior.
Qwen3 32B is a dense 32.8B-parameter model in the Qwen3 family from Alibaba's Qwen team, released in April 2025. It switches between a thinking mode for complex reasoning and a fast non-thinking mode, supports 119 languages, and has a native 32K-token context window (131K with YaRN).
GLM-5.1 is Z.ai's open-weight Mixture-of-Experts model for agentic engineering, with 744B total and 40B active parameters. It takes text input and output with a 200K-token context window and up to 128K output tokens, and is tuned for coding agents and long-running tool use.
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Access 13 models served through Phala AI on AnonRouter's privacy-first gateway, including Gemma 4 26B A4B Uncensored, Qwen 2.5 7B, and Kimi K3. Phala AI routes through an aggregator gateway that decrypts each request before forwarding it to the model, so Phala can see prompt content; AnonRouter strips the caller's identity before the request reaches it, and these routes carry no enclave attestation.
