gpt-oss-20b: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
gpt-oss-20b (High) supports text input, outputs text, and has a 131k tokens context window with knowledge up to May 2024.
Pricing for gpt-oss-20b (High) is $0.05 per 1M input tokens (competitively priced, median: $0.13) and $0.22 per 1M output tokens (moderately priced, median: $0.30).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Knowledge cutoff | May 31, 2024 |
| Context window | 131k ~197 A4 pages of size 12 Arial font |
| Total parameters | 21B |
| Active parameters | 3.6B Number of parameters active per token during inference |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, Elo
Agentic SaaS workflows
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Agentic real-world work tasks, Elo
Medical long context reasoning
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
Frequently Asked Questions
Common questions about gpt-oss-20b
gpt-oss-20b was released on August 5, 2025.
gpt-oss-20b was created by OpenAI.
gpt-oss-20b has a time to first answer token of 36.83s (high) and 1.37s (low) (based on the median across providers serving the model). gpt-oss-20b (High)'s time to first answer token is at the higher end compared to other open weight models of similar size (median: 4.56s).
gpt-oss-20b costs $0.05 (high) and $0.07 (low) per 1M input tokens and $0.22 (high) and $0.30 (low) per 1M output tokens, based on the median across providers serving the model. gpt-oss-20b (High) is very competitive on input price (median: $0.13) and better than average on output price (median: $0.30).
gpt-oss-20b costs $0.05 (high) and $0.07 (low) per 1M input tokens and $0.22 (high) and $0.30 (low) per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.067 (high) and $0.093 (low) per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, gpt-oss-20b is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
gpt-oss-20b supports text input.
gpt-oss-20b supports text output.
No, gpt-oss-20b does not support image input. It can only process text.
No, gpt-oss-20b is not multimodal. It only supports text input.
gpt-oss-20b has a context window of 131k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, gpt-oss-20b is open weights. The model weights are publicly available and can be downloaded for self-hosting.
gpt-oss-20b has 21B parameters (3.6B active).
gpt-oss-20b is a Mixture of Experts (MoE) model with 21B total parameters, but only 3.6B active parameters are used during inference.
gpt-oss-20b is released under the Apache 2.0 license. This license allows commercial use. View license
gpt-oss-20b has a knowledge cutoff of May 2024. The model's training data includes information up to this date.
Yes, gpt-oss-20b is available via API through 4 providers. Compare API providers
gpt-oss-20b is available through 4 API providers. Compare providers