GPT-OSS 20B

$0.07
Input / MTok
$0.3
Output / MTok
$0.035
Cache read / MTok

Hosted third-party inference; price is Fireworks' Standard serverless rate, not OpenAI's own API.

API identifier accounts/fireworks/models/gpt-oss-20b · vendor pricing page

Full price sheet

MetricUSD / million tokens
Input$0.07
Output$0.3
Cache read$0.035

Price history

ObservedMetric Price
2026-08-08 07:26:49 Input $0.07
2026-08-08 07:26:49 Output $0.3
2026-08-08 07:26:49 Cache read $0.035

Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.

Changes affecting this model

coverage
GPT-OSS 20B added to coverage
2026-08-08

Compare with

Models at a similar price point.

ModelInputOutput
GPT-OSS 20B $0.075$0.3 compare →
DeepSeek V4 Flash $0.14$0.28 compare →
DeepSeek V4 Flash (0731) $0.14$0.28 compare →
DeepSeek V4 Flash $0.14$0.28 compare →
Devstral Small 2 $0.1$0.3 compare →
Qwen3.5 9B $0.17$0.25 compare →