Workspace capabilities
Available models
Every language model available on the platform, with its tier and residency.
Four models run in Australia: the three Claude models on AWS Bedrock, and Gemini 2.5 Flash on Google Vertex. Everything else may be served from outside Australia. See data residency.
Each model carries a per-minute rate set by its tier. The model picker shows the current rate beside each model, and Billing covers how per-minute pricing works.
Claude, on AWS Bedrock, Australia
| Model | Tier |
|---|---|
| Claude Haiku 4.5 (default) | Fast |
| Claude Sonnet 4.6 | Balanced |
| Claude Opus 4.6 | Power |
Gemini, on Google Vertex
| Model | Tier | Residency |
|---|---|---|
| Gemini 2.5 Flash | Fast | Australia |
| Gemini 2.5 Flash-Lite | Fast | Global |
| Gemini 2.5 Pro | Balanced | Global |
| Gemini 3 Flash Preview | Fast | Global |
| Gemini 3.1 Flash-Lite | Fast | Global |
| Gemini 3.1 Pro Preview | Balanced | Global |
| Gemini 3.5 Flash | Fast | Global |
OpenAI, global
| Model | Tier |
|---|---|
| GPT-4o mini | Fast |
| GPT-4.1 | Balanced |
| GPT-4.1 nano | Fast |
| GPT-5 | Balanced |
| GPT-5 mini | Fast |
| GPT-5 nano | Fast |
| GPT-5.1 | Balanced |
| GPT-5.2 | Balanced |
| GPT-5.4 | Balanced |
| GPT-5.4 mini | Fast |
| GPT-5.4 nano | Fast |
| GPT-5.5 | Balanced |
| o1 | Power |
| o3-mini | Fast |
| o4-mini | Fast |
Groq, Cerebras and Inception, global
| Model | Provider | Tier |
|---|---|---|
| Llama 3.3 70B | Groq | Speed |
| Llama 3.1 8B | Groq | Fast |
| GPT-OSS 20B | Groq | Fast |
| GPT-OSS 120B | Groq | Fast |
| Qwen3.6 27B | Groq | Fast |
| Gemma 4 31B | Cerebras | Fast |
| Mercury 2 | Inception | Fast |
The list in your workspace is the live source of truth. Models are added and retired, so the picker can differ from the tables above. It always shows the current set, with the default marked.