InferX Endpoint | Qwen3-Coder-Next-FP8-no-thinking

Metadata

Name

Qwen3-Coder-Next-FP8-no-thinking

Provider

—

Parameter Size

—

GPU Count

1

Context Length

260000

Concurrency

6.55x

Cold Start TTFT

—

Recommended Use Cases

—

Detailed Intro

—

Log In To Use This Endpoint

This public page shows the published endpoint metadata and integration shape. Log in to get a tenant-scoped endpoint URL, inference API key, and the interactive playground. Log in

Integration

Use these values in Dify, OpenWebUI, Continue, OpenCode, or any OpenAI-compatible client that asks for a base URL, API key, and model name.

API Base URL

https://model.inferx.net/funccall/<tenant>/endpoints/Qwen3-Coder-Next-FP8-no-thinking/v1

Model Name

Qwen/Qwen3-Coder-Next-FP8

API Key

<INFERENCE_API_KEY>

An inference API key is required for this endpoint. Until one is available, the sample request below keeps the correct request shape and uses a placeholder token.

Sample REST Call

Model Spec

{
    "image": "inferx/vllm-openai:v0.20.2-cu129",
    "commands": [
        "--model",
        "Qwen/Qwen3-Coder-Next-FP8",
        "--trust-remote-code",
        "--gpu-memory-utilization",
        "0.95",
        "--enable-auto-tool-choice",
        "--tool-call-parser",
        "qwen3_coder",
        "--max-num-seqs",
        "20",
        "--uvicorn-log-level",
        "warning",
        "--max-num-batched-tokens",
        "262000",
        "--max-num-batched-tokens",
        "12288",
        "--default-chat-template-kwargs",
        "{\"enable_thinking\": false}",
        "--enable-prefix-caching",
        "--enable-chunked-prefill",
        "--tensor-parallel-size",
        "1"
    ],
    "resources": {
        "GPU": {
            "Count": 1,
            "vRam": 125900
        }
    },
    "envs": [
        [
            "VLLM_USE_DEEP_GEMM",
            "0"
        ],
        [
            "VLLM_ALLREDUCE_USE_SYMM_MEM",
            "0"
        ]
    ],
    "policy": {
        "Obj": {
            "min_replica": 0,
            "max_replica": 1,
            "standby_per_node": 1,
            "parallel": 50,
            "queue_len": 100,
            "queue_timeout": 30.0,
            "scalein_timeout": 1.0,
            "scaleout_policy": {
                "WaitQueueRatio": {
                    "wait_ratio": 0.1
                }
            },
            "runtime_config": {
                "graph_sync": false
            }
        }
    },
    "sample_query": {
        "apiType": "text2text",
        "raw_query": false,
        "path": "v1/completions",
        "prompt": "write a quick sort algorithm.",
        "prompts": [],
        "dataUrl": "",
        "max_tokens": 0,
        "body": {
            "max_tokens": "1000",
            "stream": "true",
            "temperature": "0"
        },
        "loadingTimeout": 90
    }
}

InferX Beta — Serverless GPU Inference Platform, Built for Agent-Native Workloads

Endpoint Qwen3-Coder-Next-FP8-no-thinking

Metadata

Log In To Use This Endpoint

Integration

Sample REST Call

Model Spec