Models
Model IDs, context windows and capabilities.
Pass the model ID in the model field.
| Model ID | Context window | Notes |
|---|---|---|
flash |
1,048,576 | Fastest and cheapest. Good default. |
base |
262,144 | General purpose. |
large-v2 |
1,000,000 | Most capable. Always reasons. |
large |
1,000,000 | Deprecated; use large-v2. |
Context is the combined input and output budget. Output is capped at 32,768 tokens per request on every model.
Capabilities
Section titled “Capabilities”| Capability | Chat Completions | Responses | Messages |
|---|---|---|---|
| Text input and output | ✓ | ✓ | ✓ |
| Streaming | ✓ | ✓ | ✓ |
| Function tools | ✓ | ✓ | ✓ |
Structured output (response_format / text.format) |
✓ | ✓ | |
| Reasoning effort | ✓ | ✓ | |
| Web search | ✓ | ||
| Image, audio or file input |
List models
Section titled “List models”curl https://api.solcardinference.ai/v1/models \ -H "Authorization: Bearer $SOLCARD_INFERENCE_KEY"See List models for the response, which includes each model’s price.