Inference provider
Together AI
Serverless and dedicated inference for open models.
Routing contract
https://api.together.xyz/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.
Catalog coverage
Model endpoints
| Model | Route model | Context | Input / 1M | Output / 1M | Region | Evidence |
|---|---|---|---|---|---|---|
| gpt-oss-20bRoute-ready | openai/gpt-oss-20b | 128K | $0.050 | $0.20 | — | Provider-reported |
| gpt-oss-120bRoute-ready | openai/gpt-oss-120b | 128K | $0.15 | $0.60 | — | Provider-reported |
Questions
Together AI questions
Which models does Together AI offer?+
The current source snapshot includes 2 model endpoint for Together AI: gpt-oss-20b, gpt-oss-120b. Browse all models →
How much does Together AI cost?+
For gpt-oss-20b, the cited source reports $0.050 input and $0.20 output per million tokens.
Is Together AI 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 Together AI data?+
This source snapshot was observed Aug 28, 2026 and is marked non-live until production collectors are activated.
How does Model Markets verify Together AI?+
Catalog and price claims retain their source classification. Independent telemetry will use disclosed-region standardized probes and will be presented separately. Read the methodology →