All Providers
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use InferX:
INFERX_API_KEYModels (12)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| Gemma 4 31B IT FP8gemma | gemma-4-31B-it-fp8 | $0/MTok | $0/MTok | 262.1K | ReasoningToolsOpen |
| Qwen3 Coder Next FP8 no thinkingqwen | Qwen3-Coder-Next-FP8-no-thinking | $0/MTok | $0/MTok | 260K | ToolsOpen |
| deepseek v4 flashdeepseek-flash | deepseek-v4-flash | $0/MTok | $0/MTok | 1M | ReasoningToolsOpen |
| Devstral 2 123B Instruct 2512 int4 AutoRounddevstral | Devstral-2-123B-Instruct-2512-int4-AutoRound | $0/MTok | $0/MTok | 128K | ToolsOpen |
| Agents A1 | Agents-A1 | $0/MTok | $0/MTok | 262K | ReasoningToolsOpen |
| Ornith 1.0 35B FP8ornith | Ornith-1.0-35B-FP8 | $0/MTok | $0/MTok | 262K | ReasoningToolsOpen |
| Qwen 3.6 35B A3B FP8qwen | Qwen3.6-35B-A3B-FP8 | $0/MTok | $0/MTok | 262K | ReasoningToolsOpen |
| Qwen 3.6 27B FP8qwen | Qwen3.6-27B-FP8 | $0/MTok | $0/MTok | 262.1K | ReasoningToolsOpen |
| Qwen 3.6 35B A3B fp8 no thinkingqwen | Qwen3.6-35B-A3B-fp8-no-thinking | $0/MTok | $0/MTok | 262K | ToolsOpen |
| Qwen3 Coder Next FP8qwen | Qwen3-Coder-Next-FP8 | $0/MTok | $0/MTok | 256.1K | ToolsOpen |
| Qwen3 Embedding 8Btext-embedding | Qwen3-Embedding-8B | $0/MTok | $0/MTok | 32.8K | Open |
| mimo v25mimo | mimo-v25 | $0/MTok | $0/MTok | 1M | ReasoningToolsOpen |