Context Window
131,072
Input tokens
Full-context input ≈ $0.00
Model Cost Profile
Developer: openai· Tokenizer: GPT · Quantization: bf16
Canonical ID: openai/gpt-oss-20b
Pricing updated Apr 25, 2026
Live Pricing
Input: $0.0300
Output: $0.1400
Last synced Apr 25, 2026 · MMLU score via public benchmark data
OpenAI's gpt-oss-20b model offers a substantial context window of 131,072 tokens, making it suitable for applications that require extensive text analysis, such as legal document review or long-form content generation. With an input price of $0.03 per 1 million tokens and an output price of $0.14 per 1 million tokens, teams can effectively manage costs while leveraging the model for complex tasks like customer support automation or data summarization. This pricing structure allows organizations to scale their usage based on project demands, ensuring budget-friendly access to advanced AI capabilities.
Provider Compliance
Context Window
131,072
Input tokens
Full-context input ≈ $0.00
Max Output
131,072
Completion tokens
Input Price / 1M
$0.0300
Prompt tokens
Output Price / 1M
$0.1400
Completion tokens
Top Benchmark
71.8
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for OpenAI: gpt-oss-20b. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.0300
Current Output / 1M
$0.1400
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0300 |
| Output (Completion) | $0.1400 |
Estimate monthly spend for OpenAI: gpt-oss-20b based on your workload.
Estimated Monthly Cost
$2.43
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.