gpt-oss-20B (high)
gpt-oss-20B (high) is a text-based AI model by OpenAI. It features 281 tok/s output speed, $0.06/1M input tokens pricing. It scores 24.5 on the intelligence index.
Strengths
- +Very fast output (281 tok/s)
- +Very affordable pricing ($0.06/1M tokens)
Benchmarks
Intelligence24.5Coding18.5Math89.3
MMLU-Pro
0.8
GPQA
0.7
LiveCodeBench
0.8
Intelligence
24.5
Coding
18.5
Math
89.3
Output Speed
281 tok/s
Latency (TTFT)
0.48s
Blended Price
$0.09/M
Pricing per 1M Tokens
| Input (Prompt) | $0.06 |
| Output (Completion) | $0.20 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare gpt-oss-20B (high) with:
Alternatives to gpt-oss-20B (high)
More from OpenAI
Frequently Asked Questions
How much does gpt-oss-20B (high) cost?
gpt-oss-20B (high) costs $0.06/1M input tokens and $0.20/1M output tokens.
Is gpt-oss-20B (high) good for coding?
gpt-oss-20B (high) has a lower coding score of 18.5. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is gpt-oss-20B (high)?
gpt-oss-20B (high) generates output at 281 tok/s. Time to first token is 0.48s.
Is there a free version of gpt-oss-20B (high)?
No, gpt-oss-20B (high) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to gpt-oss-20B (high)?
Last updated: