gpt-oss-20b (batch) pricing & benchmarks
gpt-oss-20b (batch) is available from OpenAI at $0.024 per million input tokens and $0.112 per million output tokens ($0.046 blended at 3:1). It accepts up to 131,072 tokens of context. gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Pricing
Per million tokens · OpenRouter
Input$0.024
Output$0.112
Blended (3:1)$0.046
Specification
openai/gpt-oss-20b:batch
Context window131K
Max output118K
ReleasedAug 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for gpt-oss-20b (batch) yet. We show nothing rather than reprinting an unverified figure.
Compare gpt-oss-20b (batch)
gpt-oss-20b (batch) vs Gemini 3.7 Flash
gpt-oss-20b (batch) vs Grok 4.6
gpt-oss-20b (batch) vs DeepSeek V4 Flash 0731
gpt-oss-20b (batch) vs Inkling Small
gpt-oss-20b (batch) vs Qwen3.7 Flash
gpt-oss-20b (batch) vs Claude Opus 5
gpt-oss-20b (batch) vs Gemini 3.6 Flash
gpt-oss-20b (batch) vs Gemini 3.5 Flash Lite
FAQ
How much does gpt-oss-20b (batch) cost?
gpt-oss-20b (batch) costs $0.024 per million input tokens and $0.112 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.046 per million tokens.
What is gpt-oss-20b (batch)'s context window?
gpt-oss-20b (batch) accepts up to 131,072 tokens of context, and can generate up to 117,964 output tokens.