InferX
inferx
Updated 1 hour ago
InferX is an AI inference platform offering hosted pay-per-token and dedicated endpoints for open models through an OpenAI-compatible API, with scale-to-zero infrastructure and selected free promotional models.
Browse 9 LLM models available from InferX. Compare prices and features.
Models (9)
| Organization | Model Name | Original Model | Input | Output | Free | |||
|---|---|---|---|---|---|---|---|---|
|
DeepSeek | DeepSeek-V4.1-Flash |
deepseek-v4.1-flash
|
$0.09 | $0.36 |
|
||
|
Z.ai | GLM-5.3-Flash |
GLM-5.3-Flash
|
$0.09 | $0.30 |
|
||
|
qwen | Qwen3.8-27B |
Qwen3.8-27B-FP8
|
$0.02 | $0.13 | |||
|
|
DeepSeek | DeepSeek-V4-Flash-Max |
deepseek-v4-flash-0731
|
$0.04 | $0.08 |
|
||
|
Alibaba | Qwen3.6-27B |
Qwen3.6-27B-FP8
|
$0.03 | $0.28 | |||
|
|
qwen | Qwen3.6-35B-A3B |
Qwen3.6-35B-A3B-FP8
|
$0.01 | $0.09 | |||
|
Gemma 4 31B |
gemma-4-31B-it-fp8
|
$0.01 | $0.04 |
|
|||
|
OpenAI | GPT OSS 20B |
gpt-oss-20b
|
$0.01 | $0.03 |
|
||
|
|
qwen | Qwen3 Coder Next |
Qwen3-Coder-Next-FP8
|
$0.18 | $0.90 |