Skip to main content
Use these models with the chat completions endpoint. Reference a model by its id (shown in each card) in the model field. All take text input and return text output.
The exact set your key can call is returned by GET /v1/models. For per-model rates, see Pricing.

What the icons mean

Tools

Function / tool calling. See Tool calling.

Reasoning

Thinks step by step before answering. See Reasoning.

Structured output

Returns JSON matching a schema. See Structured outputs.

Deepshi models

Deepshi’s own models are uncensored by default. They answer without the refusals you hit on mainstream APIs.

Deepshi 2.0

deepshi-2.0 · Context 128KLargely uncensored, with open, minimally-filtered responses. The most direct option.

Deepshi 3.0

deepshi-3.0 · Context 256KMultimodal flagship with strong visual understanding and agentic coding. Tools   Reasoning   Structured

Frontier models

The latest models from leading providers, through the same endpoint, key, and balance.

Claude Opus 4.8

claude-opus-4.8 · Context 1MAnthropic’s most capable Opus model, with deep reasoning over long, complex tasks. Tools   Reasoning   Structured

Claude Opus 4.7

claude-opus-4.7 · Context 1MOpus-family model built for long-running, asynchronous agents. Tools   Reasoning   Structured

Claude Sonnet 4.6

claude-sonnet-4.6 · Context 1MStrong all-rounder for coding, agents, and professional work. Tools   Reasoning   Structured

GPT-5.5

gpt-5.5 · Context 1MOpenAI’s frontier model for complex professional workloads. Tools   Reasoning   Structured

GPT-5.4

gpt-5.4 · Context 1MFrontier model unifying the GPT and Codex lines, strong at agentic coding. Tools   Reasoning   Structured

GPT-4.1

gpt-4.1 · Context 1MTuned for precise instruction-following and software engineering. Tools   Structured

GPT-4o

gpt-4o · Context 128KGPT-4-class intelligence that runs faster and cheaper. Solid general-purpose pick. Tools   Structured

Gemini 3.5 Flash

gemini-3.5-flash · Context 1MGoogle’s high-efficiency model with near-Pro reasoning at Flash speed and cost. Tools   Reasoning   Structured

Grok 4.3

grok-4.3 · Context 1MxAI reasoning model suited to agentic workflows and high factual accuracy. Tools   Reasoning   Structured

Grok 4.20

grok-4.20 · Context 2MFast xAI reasoning model with strong tool-calling and low hallucination. Tools   Reasoning   Structured

GLM-5.2

glm-5.2 · Context 1MLarge-scale reasoning model for long-horizon agent and engineering work. Tools   Reasoning   Structured

GLM-5.1

glm-5.1 · Context 200KA major step up in coding ability on long-horizon tasks. Tools   Reasoning   Structured

GLM-5

glm-5 · Context 200KZ.ai’s flagship open model for complex systems and agent workflows. Tools   Reasoning   Structured

Kimi K2.6

kimi-k2.6 · Context 256KBuilt for long-horizon coding, UI/UX generation, and multi-agent orchestration. Tools   Reasoning   Structured

Gemma 4 31B

gemma-4-31b-it · Context 256KA ~31B dense open model with an optional reasoning mode and native tools. Tools   Reasoning   Structured
Not sure where to start? Use deepshi-2.0 for the most uncensored responses, or deepshi-3.0 for an all-round flagship with tools and reasoning.