Today's price · per 1M tokens
Input
$0.070
per 1M tokens
Output
$0.300
per 1M tokens
Blended
$0.128
blended $/1M — 3:1 weighted input:output
Cached input
$0.035
50% of input — prompt caching
Price receipt
We read Fireworks's own pricing page on Aug 9, 2026 and found GPT OSS 20B listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 4f5353269c.
Overview
OpenAI's GPT-OSS 20B on Fireworks. $0.07/$0.30 per 1M; cached $0.035.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is better- AA Intelligence Index: 15.2 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 3.1 (Tool use, planning, autonomy)
- AA-Omniscience Index: -63 (−100–100)
- Ranks #49 of 69 benchmarked models by average score
- Ranks #109 of 161 comparably-measured models by percentile score, across 7 independent measurements
- Ranks #6 of 161 comparably-tested models by normalized performance per dollar
- Strongest at AIME 2025 — 98.7%, #3 of 37
941.5 tokens/sec output 0.47s latency to first token (TTFT)
Source: Vellum LLM Leaderboard · updated Aug 22, 2026 · See full rankings →
Specifications
- Provider
- Fireworks
- Context window
- 128K tokens
- Modality
- text
- Parameters
- 20B
- Open source
- Yes — open weights available
- Released
- Jan 1, 2026
- Status
- Current
- Last updated
- Jun 25, 2026
- Tags
Availability verified: Aug 9, 2026 — listed on Fireworks's own page