token.app › Compare › gpt-oss-120b vs Glimpse
gpt-oss-120b vs Glimpse
gpt-oss-120b is 4.6× cheaper per token on a blended 3:1 basis. Glimpse accepts the larger context window (262K).
Head to head
Blended price uses a 3:1 input:output mix
| gpt-oss-120b | Glimpse | |
|---|---|---|
| Provider | OpenAI | Elorian |
| Input $/1M | $0.150 | $0.600 |
| Output $/1M | $0.600 | $3.00 |
| Blended $/1M | $0.262 | $1.20 |
| Context window | 131K | 262K |
| Max output | 66K | 256K |
| Released | Aug 2025 | Oct 2026 |
| Licence | Open weights | Proprietary |
Choose gpt-oss-120b if…
- Costs less per token — $0.262 vs $1.20 blended
- Open weights — self-hostable
Choose Glimpse if…
- Larger context window (262K)
- Newer model (released Oct 2026)
FAQ
Which is better, gpt-oss-120b or Glimpse?
We do not hold independently-run benchmark scores covering both gpt-oss-120b and Glimpse, so we make no quality claim. Their pricing and specifications are compared on this page.
Is gpt-oss-120b cheaper than Glimpse?
gpt-oss-120b is cheaper: $0.262 versus $1.20 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.600. Output alone: $0.600 vs $3.00.
What context windows do gpt-oss-120b and Glimpse have?
gpt-oss-120b: 131,072 tokens. Glimpse: 262,144 tokens.
Who makes gpt-oss-120b and Glimpse?
gpt-oss-120b is made by OpenAI. Glimpse is made by Elorian.