token.app › Compare › gpt-oss-20b (batch) vs Gemini 3.5 Flash Lite

gpt-oss-20b (batch) vs Gemini 3.5 Flash Lite

gpt-oss-20b (batch) is 18× cheaper per token on a blended 3:1 basis. Gemini 3.5 Flash Lite accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
gpt-oss-20b (batch)Gemini 3.5 Flash Lite
ProviderOpenAIGoogle
Input $/1M$0.024$0.300
Output $/1M$0.112$2.50
Blended $/1M$0.046$0.850
Context window131K1.0M
Max output118K66K
ReleasedAug 2025Jul 2026
LicenceOpen weightsProprietary
Choose gpt-oss-20b (batch) if…
  • Costs less per token — $0.046 vs $0.850 blended
  • Open weights — self-hostable
Choose Gemini 3.5 Flash Lite if…
  • Larger context window (1.0M)
  • Newer model (released Jul 2026)
FAQ
Which is better, gpt-oss-20b (batch) or Gemini 3.5 Flash Lite?
We do not hold independently-run benchmark scores covering both gpt-oss-20b (batch) and Gemini 3.5 Flash Lite, so we make no quality claim. Their pricing and specifications are compared on this page.
Is gpt-oss-20b (batch) cheaper than Gemini 3.5 Flash Lite?
gpt-oss-20b (batch) is cheaper: $0.046 versus $0.850 per million tokens blended at 3:1 input:output. Input alone: $0.024 vs $0.300. Output alone: $0.112 vs $2.50.
What context windows do gpt-oss-20b (batch) and Gemini 3.5 Flash Lite have?
gpt-oss-20b (batch): 131,072 tokens. Gemini 3.5 Flash Lite: 1,048,576 tokens.
Who makes gpt-oss-20b (batch) and Gemini 3.5 Flash Lite?
gpt-oss-20b (batch) is made by OpenAI. Gemini 3.5 Flash Lite is made by Google.
Related comparisons
gpt-oss-20b (batch) full details Gemini 3.5 Flash Lite full details gpt-oss-20b (batch) vs Flint (free) gpt-oss-20b (batch) vs MiniMax M3.1 Flash (free) gpt-oss-20b (batch) vs DeepSeek V4.1 Flash 1017 gpt-oss-20b (batch) vs Glimpse gpt-oss-20b (batch) vs Xing4.0 29B A4B (free) gpt-oss-20b (batch) vs Beam 1.0 501B A23B