token.app › Compare › gpt-oss-20b (batch) vs Flint (free)

gpt-oss-20b (batch) vs Flint (free)

Flint (free) is free to use, against $0.046 per million tokens. Flint (free) accepts the larger context window (262K).

Head to head
Blended price uses a 3:1 input:output mix
gpt-oss-20b (batch)Flint (free)
ProviderOpenAIRecursive
Input $/1M$0.024Free
Output $/1M$0.112Free
Blended $/1M$0.046Free
Context window131K262K
Max output118K236K
ReleasedAug 2025Oct 2026
LicenceOpen weightsOpen weights
Choose gpt-oss-20b (batch) if…
  • No clear advantage on the data we hold.
Choose Flint (free) if…
  • Costs less per token — Free vs $0.046 blended
  • Larger context window (262K)
  • Newer model (released Oct 2026)
FAQ
Which is better, gpt-oss-20b (batch) or Flint (free)?
We do not hold independently-run benchmark scores covering both gpt-oss-20b (batch) and Flint (free), so we make no quality claim. Their pricing and specifications are compared on this page.
Is gpt-oss-20b (batch) cheaper than Flint (free)?
Flint (free) is cheaper: Free versus $0.046 per million tokens blended at 3:1 input:output. Input alone: $0.024 vs Free. Output alone: $0.112 vs Free.
What context windows do gpt-oss-20b (batch) and Flint (free) have?
gpt-oss-20b (batch): 131,072 tokens. Flint (free): 262,144 tokens.
Who makes gpt-oss-20b (batch) and Flint (free)?
gpt-oss-20b (batch) is made by OpenAI. Flint (free) is made by Recursive.
Related comparisons