Groq
Low-latency hosted inference on GroqCloud.
- Models tracked
- 2
- Route-ready
- 2
- Input from
- $0.075
- Output from
- $0.30
Catalog Coverage
Model Endpoints
| Model | Route model | Context | Input / 1M | Output / 1M | Region | Evidence |
|---|---|---|---|---|---|---|
| gpt-oss-20bRoute-ready | openai/gpt-oss-20b | 131K | $0.075 | $0.30 | — | Provider-reported |
| gpt-oss-120bRoute-ready | openai/gpt-oss-120b | 131K | $0.15 | $0.60 | — | Provider-reported |
Routing Contract
https://api.groq.com/openai/v1These public route targets identify where and how a model can be requested. Model Markets does not hold provider keys or send inference traffic from this interface.
Provider records describe a serving surface, not the underlying model. Pricing, quantization, region, service tier, retention policy, and measured performance remain endpoint-specific.
Questions
Groq Questions
Which models does Groq offer?+
The current source snapshot includes 2 model endpoint for Groq: gpt-oss-20b, gpt-oss-120b. Browse all models →
How much does Groq cost?+
For gpt-oss-20b, the cited source reports $0.075 input and $0.30 output per million tokens.
Is Groq 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 Groq data?+
The cited source snapshot was observed Aug 28, 2026; availability may have changed since then.
How does Model Markets verify Groq?+
Catalog and price claims retain their source classification; independent measurements are labeled separately when available. Read the methodology →