InferX
Updated Sep 11, 2026
| Model | 1M input | 1M output | 1M cache read | Context | Released | Tags |
|---|
| Agents-A1 | free | free | — | 262k | Jun 26, 2026 | free |
| Ornith-1.0-35B-FP8 | free | free | — | 262k | Jun 25, 2026 | free |
| DeepSeek V4 Flash | free | free | — | 1.0M | Apr 24, 2026 | free |
| Qwen3.6 27B FP8 | free | free | — | 262k | Apr 22, 2026 | free |
| mimo-v25 | free | free | — | 1.0M | Apr 22, 2026 | free |
| Qwen3.6 35B A3B FP8 | free | free | — | 262k | Apr 17, 2026 | free |
| Qwen3.6-35B-A3B-fp8-no-thinking | free | free | — | 262k | Apr 17, 2026 | free |
| Gemma 4 31B IT FP8 | free | free | — | 262k | Apr 2, 2026 | free |
| Qwen3 Coder Next FP8 | free | free | — | 256k | Feb 3, 2026 | free |
| Qwen3-Coder-Next-FP8-no-thinking | free | free | — | 260k | Feb 3, 2026 | free |
| Devstral-2-123B-Instruct-2512-int4-AutoRound | free | free | — | 128k | Dec 9, 2025 | free |
| Qwen3 Embedding 8B | free | free | — | 33k | Jun 5, 2025 | free |