DInference 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 6 models on this page. Coverage spans text and chat (6). The lowest-priced model hosted here is GPT OSS 120B.
DInference is the lowest paid channel for 1 model that has at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| GPT OSS 120Bgpt-oss-120b | $0.068 | $0.27 | — | 131,072 | 2.0× pricier |
| MiniMax-M2.5minimax-m2.5 | $0.22 | $0.88 | — | 200,000 | Lowest anywhere |
| GLM-4.7glm-4.7 | $0.45 | $1.65 | — | 200,000 | 2.1× pricier |
| GLM-5glm-5 | $0.75 | $2.40 | — | 200,000 | 1.6× pricier |
| GLM-5.2glm-5.2 | $1.25 | $3.89 | — | 1,000,000 | 3.9× pricier |
| GLM-5.1glm-5.1 | $1.25 | $3.89 | — | 200,000 | 2.2× pricier |