Provider Models
InferX LLM Models
Compare InferX models with normalized token pricing, context window limits, modalities, and capability metadata. This page is optimized for provider-level model research.
12 active models listed. Open all InferX models filters
| Model | Context | Input Price | Output Price |
|---|---|---|---|
|
Agents-A1
inferx/Agents-A1
|
262,000 | $0/1M | $0/1M |
|
deepseek-v4-flash
inferx/deepseek-v4-flash
|
1,000,000 | $0/1M | $0/1M |
|
Devstral-2-123B-Instruct-2512-int4-AutoRound
inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound
|
128,000 | $0/1M | $0/1M |
|
Gemma 4 31B IT FP8
inferx/gemma-4-31B-it-fp8
|
262,144 | $0/1M | $0/1M |
|
mimo-v25
inferx/mimo-v25
|
1,000,000 | $0/1M | $0/1M |
|
Ornith-1.0-35B-FP8
inferx/Ornith-1.0-35B-FP8
|
262,000 | $0/1M | $0/1M |
|
Qwen3.6 27B FP8
inferx/Qwen3.6-27B-FP8
|
262,144 | $0/1M | $0/1M |
|
Qwen3.6 35B A3B FP8
inferx/Qwen3.6-35B-A3B-FP8
|
262,000 | $0/1M | $0/1M |
|
Qwen3.6-35B-A3B-fp8-no-thinking
inferx/Qwen3.6-35B-A3B-fp8-no-thinking
|
262,000 | $0/1M | $0/1M |
|
Qwen3 Coder Next FP8
inferx/Qwen3-Coder-Next-FP8
|
256,144 | $0/1M | $0/1M |
|
Qwen3-Coder-Next-FP8-no-thinking
inferx/Qwen3-Coder-Next-FP8-no-thinking
|
260,000 | $0/1M | $0/1M |
|
Qwen3-Embedding-8B
inferx/Qwen3-Embedding-8B
|
32,768 | $0/1M | $0/1M |