Catalog models
19
Model data
Compare model cost, context, and performance fields.
AetherGate keeps current provider/model metadata in one directory. Newly released models can be selectable before AetherGate has enough traffic to publish its own latency or uptime measurements.
Provider connectors
8
Measured avg TTFT
275 ms
Largest context
1,050K
| Model | Provider | Input / 1M | Output / 1M | TTFT | Uptime |
|---|---|---|---|---|---|
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | Not measured | Not measured |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | Not measured | Not measured |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | Not measured | Not measured |
| Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | Not measured | Not measured |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | Not measured | Not measured |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | Not measured | Not measured |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | 380 ms | 99.9% |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | 620 ms | 99.9% |
| GPT-5.6 Sol | OpenAI | $4.00 | $20.00 | 430 ms | 99.9% |
| GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | 300 ms | 99.9% |
| GPT-5.6 Luna | OpenAI | $0.10 | $0.50 | 180 ms | 99.9% |
| Gemini 3.8 Flash | Google AI Studio | $0.75 | $3.75 | 190 ms | 99.9% |
| GPT-OSS 120B on Groq | Groq LPU Cloud | $0.15 | $0.60 | 90 ms | 99.9% |
| GPT-OSS 20B on Groq | Groq LPU Cloud | $0.07 | $0.30 | 65 ms | 99.9% |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | 240 ms | 99.5% |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $3.96 | 420 ms | 99.5% |
| Mistral Medium 3.5 | Mistral AI | $1.50 | $7.50 | 290 ms | 99.9% |
| Mistral Small 4 | Mistral AI | $0.15 | $0.60 | 180 ms | 99.9% |
| AetherGate Smart Router (Auto) | AetherGate Virtual Route | $0.20 | $1.20 | 190 ms | 99.99% |
Pricing/context fields are catalog metadata. AetherGate-specific performance fields are shown only when measured.