{
  "name": "InferX",
  "url": "https://model.inferx.net/endpoints",
  "free_type": "Free Developer Tier",
  "notes": "The Grant: InferX provides zero-cost inference endpoints for cutting-edge open models including Qwen 3.6, Gemma 4, and DeepSeek variants.\nThe Output: Ultra-low latency OpenAI-compatible completions with streaming and structured output support.\nThe Process: Sign in to generate an API key and query endpoint URLs directly.\nThe Condition: Rate-limited for community development and prototyping.",
  "timeout": "120s",
  "verified": "2026-11-08",
  "models": [
    {
      "name": "Qwen3.6 35B A3B FP8",
      "cost": "$0",
      "context": "255.9K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "deepseek-v4-flash",
      "cost": "$0",
      "context": "1.0M",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Ornith-1.0-35B-FP8",
      "cost": "$0",
      "context": "255.9K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Qwen3.6 27B FP8",
      "cost": "$0",
      "context": "256K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "mimo-v25",
      "cost": "$0",
      "context": "1.0M",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Qwen3 Coder Next FP8",
      "cost": "$0",
      "context": "250.1K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Agents-A1",
      "cost": "$0",
      "context": "255.9K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Devstral-2-123B-Instruct-2512-int4-AutoRound",
      "cost": "$0",
      "context": "125K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Qwen3-Embedding-8B",
      "cost": "$0",
      "context": "32K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Qwen3.6-35B-A3B-fp8-no-thinking",
      "cost": "$0",
      "context": "255.9K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Gemma 4 31B IT FP8",
      "cost": "$0",
      "context": "256K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    },
    {
      "name": "Qwen3-Coder-Next-FP8-no-thinking",
      "cost": "$0",
      "context": "253.9K",
      "rpm": "60",
      "tpm": "Not published",
      "rpd": "2,000",
      "tpd": "Not published",
      "verified": "2026-11-08"
    }
  ],
  "verified_method": "api",
  "docs_url": "https://model.inferx.net/endpoints",
  "access_method": "api_key",
  "artifact": "code",
  "base_url": "https://model.inferx.net/endpoints/v1",
  "channel": "web"
}