gpt-oss-20b vs Gemini 2.5 Flash Lite
API pricing, benchmark indices and specs — updated 19 October 2026.
openai · A · Open weights
Params
21.5 B
Context
131,072
30d
5.7 M
apache-2.0 · commercial OK
google · B · API-only
Input / 1M
$0.10
Output / 1M
$0.40
AA index
10.4
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-20b | Gemini 2.5 Flash Lite |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 21.5 B | n/a — API-only |
| Architecture | GptOssForCausalLM | n/a — API-only |
| Context length | 131,072 | 1,048,576 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 5,656,843 | n/a — API-only |
| Downloads all time | 105.0 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2025-08-04 | n/a — API-only |
| API input price / 1M tokens | $0.018 | $0.10 |
| API output price / 1M tokens | $0.09 | $0.40 |
| Est. cost per 1M input + 1M output tokens | $0.11 | $0.50 |
| Cached input / 1M tokens | $0.009 | $0.01 |
| AA Intelligence Index | 10 | 10.4 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 32,768 | 65,535 |
| API providers | 10 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-20b
$0.11
Gemini 2.5 Flash Lite
$0.50
gpt-oss-20b is 4.6× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-oss-20b · fp16 @ 128K ctx
82.4 GB / 24 GB