GPT Oss 20b API Pricing
GPT Oss 20b costs $0.05 per 1M input tokens and $0.2 per 1M output tokens on OpenAI's API. Prices are provider list prices in USD, refreshed as sources update; see the GPT Oss 20b model profile for capability scores.
Price List
| Rate | Price (USD) | Notes |
|---|---|---|
| Input | $0.05 | per 1M tokens |
| Output | $0.2 | per 1M tokens |
| Blended input + output | $0.25 | 1M in + 1M out at list price |
| Context window | 131K tokens |
What a Workload Costs
Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of GPT Oss 20b.
| Workload | Cost | Tokens |
|---|---|---|
| Short chat turn | $0.00015 | 1K in / 500 out |
| Summarize a long document | $0.00540 | 100K in / 2K out |
| Agentic coding session | $0.045 | 500K in / 100K out |
| 1M input + 1M output tokens | $0.250 | 1M in / 1M out |
Effective Cost
In AI IQ's scoring, GPT Oss 20b's list price is adjusted by a token-usage multiplier of 0.775 (measured from real benchmark runs), giving an effective cost of $0.1937 per 1M input + output tokens. That places it #1 of 117 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.