first-partycommon.labs_models

InferX

4 published models are listed on InferX. Prices shown are this provider's own listings and may differ from first-party.

inferx/docs ↗INFERX_API_KEY@ai-sdk/openai-compatible

Models

Labs

Free tier

Changes 30d

01Catalog

All 4 models on InferX

Filter by lab. Click a row for the model's full profile.

Model	Lab	Input	Output	Context	Flags
DeepSeek V4 Flash deepseek-v4-flash	DeepSeek	Not listed	Not listed	1,000,000	reasoningFreeopen weights
Qwen3.6 35B A3B FP8 Qwen3.6-35B-A3B-FP8	Alibaba	Not listed	Not listed	262,000	reasoningFreeopen weights
Qwen3 Coder Next FP8 Qwen3-Coder-Next-FP8	Alibaba	Not listed	Not listed	256,144	Freeopen weights
Qwen3 Embedding 8B Qwen3-Embedding-8B	Alibaba	Not listed	Not listed	32,768	Freeopen weights

02Activity

2026-08-16AddedAgents-A1offering → new

2026-08-16AddedDeepSeek V4 Flashoffering → new

2026-08-16AddedDevstral-2-123B-Instruct-2512-int4-AutoRoundoffering → new

2026-08-16Addedmimo-v25offering → new

2026-08-16AddedOrnith-1.0-35B-FP8offering → new

2026-08-16Removedqwen3-5-122b-a10b-nvfp4offering removed → new

2026-08-16AddedQwen3.6-35B-A3B-fp8-no-thinkingoffering → new

2026-08-16Removedqwen3-coder-next-fp8-1moffering removed → new

2026-08-16AddedQwen3-Coder-Next-FP8-no-thinkingoffering → new

2026-08-16AddedQwen3 Embedding 8Boffering → new

2026-07-11ContextGemma 4 31B IT FP8Context window 262,144 → new

2026-07-11ContextGemma 4 31B IT FP8Max output 8,192 → new

2026-07-11Contextqwen3-5-122b-a10b-nvfp4Max output 8,192 → new

2026-07-11ContextQwen3.6 27B FP8Context window 262,144 → new

2026-07-11ContextQwen3.6 27B FP8Max output 8,192 → new

2026-07-11ContextQwen3.6 35B A3B FP8Max output 8,192 → new

2026-07-11ContextQwen3 Coder Next FP8Max output 8,192 → 65,536

2026-07-11Contextqwen3-coder-next-fp8-1mMax output 8,192 → 65,536

2026-05-22AddedGemma 4 31B IT FP8offering → new

2026-05-22Addedqwen3-5-122b-a10b-nvfp4offering → new