GPT Oss 120b API Pricing

These are the tracked rates, not a live quote. Hosted-provider choice, region, long-context tiers, caching, batch discounts, and temporary promotions can change the actual bill. Open-weight availability does not mean hosted inference is free. Workload examples assume the listed standard input and output rates, with no cache hits or discounts.

OpenAI pricing catalog — check current offerings and rate tiers. This catalog may not list historical models or third-party hosted endpoints.

No model-specific official reference is recorded for this entry. Confirm the current rates directly with your inference provider.

Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of GPT Oss 120b.

In AI IQ's scoring, GPT Oss 120b's list price is adjusted by a token-usage multiplier of 0.931 (measured from real benchmark runs), giving an effective cost of $0.6934 per 1M input + output tokens. That places it #30 of 153 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.

Models with a lower effective cost that score within a few IQ points of GPT Oss 120b (IQ 98), or better.