InferX is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.
It lists 12 models on this page. 12 are offered at $0. Coverage spans text and chat (11) and embeddings (1). The lowest-priced model hosted here is DeepSeek V4 Flash.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| DeepSeek V4 Flashdeepseek-v4-flash | Free | — | 1,000,000 | — | |
| MiMo-V2.5mimo-v25 | Free | — | 1,000,000 | — | |
| Qwen3-Embedding-8BEmbeddingQwen3-Embedding-8B | Free | — | 32,768 | — | |
| Qwen3.6 35B A3B FP8Qwen3.6-35B-A3B-FP8 | Free | — | 262,000 | Only channel | |
| Qwen3 Coder Next FP8Qwen3-Coder-Next-FP8 | Free | — | 256,144 | Only channel | |
| Agents-A1Agents-A1 | Free | — | 262,000 | Only channel | |
| Devstral-2-123B-Instruct-2512-int4-AutoRoundDevstral-2-123B-Instruct-2512-int4-AutoRound | Free | — | 128,000 | Only channel | |
| Gemma 4 31B IT FP8gemma-4-31B-it-fp8 | Free | — | 262,144 | Only channel | |
| Ornith-1.0-35B-FP8Ornith-1.0-35B-FP8 | Free | — | 262,000 | Only channel | |
| Qwen3.6 27B FP8Qwen3.6-27B-FP8 | Free | — | 262,144 | Only channel | |
| Qwen3.6-35B-A3B-fp8-no-thinkingQwen3.6-35B-A3B-fp8-no-thinking | Free | — | 262,000 | Only channel | |
| Qwen3-Coder-Next-FP8-no-thinkingQwen3-Coder-Next-FP8-no-thinking | Free | — | 260,000 | Only channel |