GPT Oss 20b API Pricing
GPT Oss 20b has tracked API rates of $0.07 per 1M input tokens and $0.215 per 1M output tokens. Rates are in USD from the AI IQ dataset; see the GPT Oss 20b model profile for capability scores.
Price List
| Rate | Price (USD) | Notes |
|---|---|---|
| Input | $0.07 | per 1M tokens |
| Output | $0.215 | per 1M tokens |
| Blended input + output | $0.285 | 1M in + 1M out at list price |
| Context window | 131K tokens |
Pricing References and Billing Caveats
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.
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 | $0.00018 | 1K in / 500 out |
| Summarize a long document | $0.00743 | 100K in / 2K out |
| Agentic coding session | $0.057 | 500K in / 100K out |
| 1M input + 1M output tokens | $0.285 | 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 0.859, giving an effective cost of $0.2449 per 1M input + output tokens. That places it #13 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.
Cheaper Alternatives at Similar Capability
Models with a lower effective cost that score within a few IQ points of GPT Oss 20b (IQ 93), or better.
| Model | Provider | IQ | Effective Cost / 1M |
|---|---|---|---|
| mimo-v2.5 | Xiaomi | 108 | $0.2427 |
| gemma-4-31b | 101 | $0.1371 | |
| gemma-4-26b | 99 | $0.1371 | |
| nemotron-3-nano | US (Other) | 97 | $0.1627 |
| gemma-4-12b | 95 | $0.1421 | |
| Qwen3.7 Flash | Alibaba | 94 | $0.1486 |