LIVE Cheapest paid: Granite 4.0 Micro $0.017/Mtok in 173 models tracked Updated Jul 10, 2026
Jul 10, 2026
ModelPriceWatch$/Mtok
Pricing / Fireworks / GPT OSS 20B

GPT OSS 20B

by Fireworks · 20B parameters

Current budget Open weights cheap tier

Pricing · per 1M tokens

Input
$0.070
per million tokens
Output
$0.300
per million tokens
Cached input$0.035/Mtok (50% of input — prompt caching)
Blended avg cost*$0.185/Mtok

Available on 2 hosts · cheapest first

GPT-OSS 20B is sold by 2 providers. Prices are per 1M tokens (blended = avg of input & output). This is an open-weights model with no first-party API here — “vs cheapest” compares each host to the lowest blended price.

Host Input Output Blended vs cheapest
Fireworks cheapest $0.070 $0.300 $0.185
Groq details → $0.075 $0.300 $0.188 +1%

Each host links to its provider page and official pricing. Prices refresh twice daily.

Overview

OpenAI's GPT OSS 20B on Fireworks. $0.07/$0.30 per 1M; cached $0.035.

Run it yourself

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

Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

98.7%
avg benchmark score
533.5
perf / $/Mtok
AIME 2025
98.7%
How it stacks up
  • Ranks #1 of 35 benchmarked models by average score
  • Ranks #1 of 35 comparably-tested models by normalized performance per dollar top value
  • Strongest at AIME 2025 — 98.7%, #3 of 58
Inference speed: 564 tokens/sec

Source: Vellum LLM Leaderboard · Updated Jul 1, 2026 · See full rankings →

Specifications

ProviderFireworks
Context window128K tokens
Modalitytext
Parameters20B
Open sourceYes — open weights available
ReleasedJan 1, 2026
StatusCurrent
Last updatedJun 25, 2026
Tagsopen-weights budget caching

Cost calculator

1K tokens (in)$0.00007
1K tokens (out)$0.0003
100K tokens (in)$0.007
100K tokens (out)$0.030
1M tokens (in)$0.070
1M tokens (out)$0.300
10M tokens (blended)$1.85
Full calculator →

At a glance

Input$0.070/M
Output$0.300/M
Blended$0.185/M
Context128K
Tiercheap

Embed this price

A live, auto-updating badge for your README or docs:

GPT OSS 20B live API price

Price history

Last updated: Jul 10, 2026 · price links to the official provider pricing page (source above)

No price changes detected — this model's pricing has been stable since we began tracking it.

Compare GPT OSS 20B

Featured in these rankings

Related models