What they do
InferX provides serverless, OpenAI-compatible inference endpoints and configurable GPU deployments for agent, coding, retrieval, and model-serving workloads.
$10 off the fastest Kimi K3 and GLM 5.2 from Synthetic
Provider details
InferX
Learn more about this provider, then browse the models currently listed under it.
inferxinferx
Latest news about InferX
About InferX
How they were founded
Public sources reviewed for this seed data do not clearly disclose InferX's founders, founding year, or headquarters.
Sources
Quick Info
- Organization
- InferX
- SDK package
- @ai-sdk/openai-compatible
- Synced at
- Jul 11, 2026
Models served
12 models available through InferX
These model results are sorted newest first so you can quickly see the latest options from this provider.
InferX
Input
Output
InferXornith
Input
Output
InferXdeepseek-flash
Input
Output
InferXmimo
Input
Output
InferXqwen
Input
Output
InferXqwen
Qwen3.6-35B-A3B-fp8-no-thinking
Qwen3.6-35B-A3B-fp8-no-thinkingInferXReleased Apr 17, 2026262,000 token context windowSubscription plan pricing
Input
Output
InferXqwen
Input
Output
InferXgemma
Input
Output
InferXqwen
Qwen3-Coder-Next-FP8-no-thinking
Qwen3-Coder-Next-FP8-no-thinkingInferXReleased Feb 3, 2026260,000 token context windowSubscription plan pricing
Input
Output
InferXqwen
Input
Output
InferXdevstral
Devstral-2-123B-Instruct-2512-int4-AutoRound
Devstral-2-123B-Instruct-2512-int4-AutoRoundInferXReleased Dec 9, 2025128,000 token context windowSubscription plan pricing
Input
Output
InferXtext-embedding
Input
Output