Appendix A: Supported Models Reference
Complete list of models available in Azimuth Orion (as of plugin version 1.0):
xAI (Grok)
| Model ID | Display Name | Context Window | Max Output | Vision | Cost Tier | Default Timeout |
|---|---|---|---|---|---|---|
| grok-code-fast-1 | Grok Code Fast | 128k tokens | 32k | No | Very Low | 60s |
| grok-3 | Grok 3 | 131k tokens | 32k | No | Low | 75s |
| grok-4 | Grok 4 | 256k tokens | 32k | No | Medium | 90s |
| grok-4-turbo | Grok 4 Turbo | 256k tokens | 32k | No | Medium | 90s |
| grok-vision | Grok Vision | 128k tokens | 32k | Yes | Medium | 75s |
Notes:
- grok-code-fast-1: Best value for general UE5 questions
- grok-vision: Best xAI option for screenshots
OpenAI
| Model ID | Display Name | Context Window | Max Output | Vision | Cost Tier | Default Timeout |
|---|---|---|---|---|---|---|
| gpt-4o | GPT-4o | 128k tokens | 16k | Yes | High | 60s |
| gpt-4o-mini | GPT-4o Mini | 128k tokens | 16k | Yes | Low | 60s |
| gpt-4-turbo | GPT-4 Turbo | 128k tokens | 4k | Yes | High | 60s |
| gpt-3.5-turbo | GPT-3.5 Turbo | 16k tokens | 4k | No | Very Low | 30s |
| o1 | o1 | 128k tokens | 32k | No | Very High | 90s |
| o1-mini | o1 Mini | 128k tokens | 32k | No | High | 60s |
| o3-mini | o3 Mini | 128k tokens | 32k | No | High | 60s |
Notes:
- GPT-4o: Industry standard for vision, excellent quality
- GPT-4o mini: Budget-friendly with vision support
- o1 series: Advanced reasoning, very expensive
Anthropic (Claude)
| Model ID | Display Name | Context Window | Max Output | Vision | Cost Tier | Default Timeout |
|---|---|---|---|---|---|---|
| claude-opus-4 | Claude Opus 4 | 200k tokens | 16k | Yes | Very High | 90s |
| claude-sonnet-4-5 | Claude Sonnet 4.5 | 200k tokens | 16k | Yes | High | 75s |
| claude-3-5-sonnet | Claude 3.5 Sonnet | 200k tokens | 8k | Yes | Medium | 75s |
| claude-haiku-4 | Claude Haiku 4 | 200k tokens | 8k | Yes | Low | 60s |
Notes:
- Claude Opus 4: Top-tier quality, 200k context window (huge Blueprints)
- Claude 3.5 Sonnet: Excellent balance of speed, cost, and quality
Google (Gemini)
| Model ID | Display Name | Context Window | Max Output | Vision | Cost Tier | Default Timeout |
|---|---|---|---|---|---|---|
| gemini-pro-1.5 | Gemini Pro 1.5 | 1M+ tokens | 32k | Yes | Medium | 90s |
| gemini-flash-1.5 | Gemini Flash 1.5 | 1M+ tokens | 32k | Yes | Low | 60s |
| gemini-pro-vision | Gemini Pro Vision | 128k tokens | 8k | Yes | Medium | 75s |
Notes:
- Gemini Pro 1.5: Massive context window (1M+ tokens—can fit entire codebases)
- Gemini Flash 1.5: Fast, low cost, still huge context
Legend
Context Window: Maximum input tokens (your question + attached context)
Max Output: Maximum completion tokens (AI response length)
Vision: Supports image input (screenshots)
Cost Tier: Relative pricing (Very Low < Low < Medium < High < Very High)
Default Timeout: Recommended HTTP timeout for this model