Inference provider
DeepInfra
Inference provider serving gpt-oss-120b.
Provider records describe a serving surface, not the underlying model. Pricing, quantization, region, service tier, retention policy, and measured performance remain endpoint-specific.
Catalog coverage
Model endpoints
| Model | Endpoint | Context | Input / 1M | Output / 1M | Region | Evidence |
|---|---|---|---|---|---|---|
| gpt-oss-120bAvailable | deepinfra/bf16 | 131.1K | $0.037 | $0.17 | Provider global routing | Provider-reported |
Questions
DeepInfra questions
Which models does DeepInfra offer?+
The current source snapshot includes 1 model endpoint for DeepInfra: gpt-oss-120b. Browse all models →
How much does DeepInfra cost?+
For gpt-oss-120b, the cited source reports $0.037 input and $0.17 output per million tokens.
Is DeepInfra the fastest provider?+
Model Markets has not run approved independent probes for this delivery, so it does not make a fastest-provider claim.
How current is DeepInfra data?+
This source snapshot was observed Aug 18, 2026 and is marked non-live until production collectors are activated.
How does Model Markets verify DeepInfra?+
Catalog and price claims retain their source classification. Independent telemetry will use disclosed-region standardized probes and will be presented separately. Read the methodology →