Claude Fable 5.1
A current reasoning model from Anthropic, available in Okou's public model catalog.
VM0 is now Okou. Same team, same product, new name.
AI models on Okou
Current models available to your agents, what each is good at, and when to pick it.
Claude Fable 5
Anthropic's premium frontier model for the hardest reasoning and long-horizon agentic runs. Always-on thinking, top SWE-bench Pro scores, at a premium above Opus-tier pricing.
Claude Opus 5
Anthropic's flagship for agentic coding and long-horizon work. State of the art on Frontier-Bench and GDPval-AA, at Opus 4.8's $5/$25 pricing.
Claude Opus 4.8
Anthropic's newest Claude 4 flagship. Leads SWE-bench Pro and OSWorld-Verified at release, with dynamic workflows and a 3× cheaper fast mode.
Claude Sonnet 5
The best balance of speed and intelligence in the Sonnet tier. Near-Opus coding and agentic quality at Sonnet cost, with adaptive thinking on by default.
Claude Sonnet 4.6
The default for most Okou agents. Strong tool-routing accuracy, good long-context behaviour, and the credit baseline. Every other model is priced relative to Sonnet 4.6.
GPT 5.6 Sol
OpenAI's newest flagship reasoning model, in preview on Okou. Top-tier coding and tool-use, routed through the Codex framework.
GPT 5.6 Terra
The balanced workhorse of the GPT-5.6 family, in preview on Okou. Strong coding and tool-use at half the flagship credit cost.
GPT 5.6 Luna
The fast, economy tier of the GPT-5.6 family, in preview on Okou. Built for bulk work and latency-sensitive steps at the lowest GPT-5.6 credit cost.
GPT-5.5
OpenAI's flagship reasoning model. Top-tier coding and tool-use, routed through the Codex framework on Okou.
DeepSeek V4 Pro
DeepSeek's flagship reasoning model. 1M-token context, native Responses API, and the $ Built-in price tier.
DeepSeek V4 Flash
Open-weight 284B MoE built for agent work. 82.7 on Terminal-Bench 2.1, a 1M-token context window, and Okou's cheapest price tier.
GPT Image 1
OpenAI's text-to-image model. Strong on stylised illustration, character work and editing.
GPT Image 2
OpenAI's newer image model for generation and editing, with flexible sizing and stronger prompt adherence than GPT Image 1.
Nano Banana 2
A current image-generation model from Google, available in Okou's public model catalog.
Nano Banana 2 Lite
A current image-generation model from Google, available in Okou's public model catalog.
FLUX.2 Pro
A current image-generation model from Black Forest Labs, available in Okou's public model catalog.
Ideogram 4
A current image-generation model from Ideogram, available in Okou's public model catalog.
Seedream 5 Pro
A current image-generation model from ByteDance, available in Okou's public model catalog.
Qwen Image 3
A current image-generation model from Alibaba, available in Okou's public model catalog.
Seedance 2.5
ByteDance's 30-second video model with native audio and up to 50 multimodal references.
Seedance 2.0
ByteDance's Seedance 2.0. Cheapest per-second video in the curated lineup — the right pick for bulk and cost-driven generation.
Seedance 1.5 Pro
A current video-generation model from ByteDance, available in Okou's public model catalog.
Veo 3.1 Fast
Google's text-to-video model with native audio. Fast generation, cinematic style and synchronised soundtrack in a single pass.
Kling V3 4K
Kuaishou's Kling V3 4K. Stylised aesthetic, long clips up to 15 seconds, 4K output — the ceiling for editorial and anime-style video.
MiniMax H3
MiniMax's multimodal video model with native stereo audio, 2K output and reference-guided generation.
