Openai-r openai/gpt-5-nano - chat model
Models & APIs
Filter the unified API by capability, provider and release status.
Openai-r openai/gpt-5.1 - chat model
Openai-r openai/gpt-5.2 - chat model
Openai-r openai/gpt-5.4 - chat model
Kimi K2.6 by Moonshot AI — general-purpose chat model with 262K-token context. Strong cost efficiency. OpenAI-compatible: pass model=kimi/k2.6 to /v1/chat/completions.
Kimi K2.7 Code by Moonshot AI — code-specialised model with 262K-token context. Supports thinking (extra_body) for extended reasoning. OpenAI-compatible: pass model=kimi/k2.7-code to /v1/chat/completions.
Kimi K2.7 Code Highspeed by Moonshot AI — faster code model with 262K-token context. Higher throughput at a small premium. OpenAI-compatible: pass model=kimi/k2.7-code-highspeed to /v1/chat/completions.
Kimi K3 by Moonshot AI — latest flagship reasoning model with 1M-token context. Uses reasoning_effort for controlled chain-of-thought. OpenAI-compatible: pass model=kimi/k3 to /v1/chat/completions.
Qwen 3 Coder Flash available through standard SkillBoss access.
Qwen 3 Coder Plus available through standard SkillBoss access.
Qwen 3.5 Flash available through standard SkillBoss access.
Qwen Coder Plus available through standard SkillBoss access.
Qwen Flash: Advanced AI chat model for natural language processing, text generation, and conversational AI tasks. Integrate with Claude Code, Cursor, and other AI agents for automated workflows.
Qwen Max: Advanced AI chat model for natural language processing, text generation, and conversational AI tasks. Integrate with Claude Code, Cursor, and other AI agents for automated workflows.
Qwen Plus: Advanced AI chat model for natural language processing, text generation, and conversational AI tasks. Integrate with Claude Code, Cursor, and other AI agents for automated workflows.
Qwen VL Max available through standard SkillBoss access.
Qwen VL Plus available through standard SkillBoss access.
Qwen3.7 Max, Alibaba's current flagship Qwen model, with thinking and non-thinking modes and up to 1M-token context.