Requesty
Sign in

identity

open weights
Fireworks AI logo

gpt-oss-20bFireworks AI

in /1M$0.07input tokens
out /1M$0.30output tokens
context131K66K out
trainingnoon your prompts
api
chat
hosting
US
model lab
OpenAI
weights
open
added
August 2025
model id
fireworks/gpt-oss-20b

capabilities 2/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

2 providers serve gpt-oss-20b. This page is one of them. Compare all endpoints

pricing

no markup
input
$0.07
output
$0.30
cache write
-
cache read
$0.04

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.0100
1M in + 100K out$0.10
10M in + 1M out$1.00

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12

no measured traffic for this endpoint yet. pricing above is the provider's own

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
MMLU Pro71.8
LiveCodeBench65.2
Math Index62.3
AIME 202562.3
GPQA Diamond61.1
τ²-Bench50.3
Intelligence Index10.0
Humanity's Last Exam5.3
Terminal-Bench Hard4.5
9 evalsmean43.6

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-08-05.

policy

data terms
retention
none
trains on prompts
no
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. Fireworks Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
fireworks/gpt-oss-20b

this id pins the fireworks ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="fireworks/gpt-oss-20b",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

GPT-OSS-20B is OpenAI's lightweight open-weight model with 21.5 billion total parameters (3.6 billion active, Mixture-of-Experts). Optimized for lower latency and local or specialized use cases including agentic tasks, chain-of-thought reasoning, and web browsing. Released under Apache 2.0 license.

questions 6

How much does gpt-oss-20b cost?
gpt-oss-20b is priced at $0.07 per million input tokens and $0.30 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of gpt-oss-20b?
gpt-oss-20b has a context window of 131K tokens, with a maximum output of 66K tokens per response. That is roughly 175 words of input you can fit in a single prompt.
How does gpt-oss-20b perform on benchmarks?
gpt-oss-20b scores 71.8% on MMLU Pro, 65.2% on LiveCodeBench, 62.3% on Math Index. The benchmarks pane shows every published result, each normalised to 100.
What can gpt-oss-20b do?
gpt-oss-20b supports extended reasoning, prompt caching. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use gpt-oss-20b with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "fireworks/gpt-oss-20b". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run gpt-oss-20b through Requesty?
Yes. gpt-oss-20b runs through Requesty's OpenAI-compatible API, served from Fireworks AI. You do not host the model yourself: point base_url at Requesty, set the model to "fireworks/gpt-oss-20b", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from fireworks ai 8

Other Fireworks AI endpoints
endpointctxin /M
deepseek-v4.1-flash1.0M$0.22
deepseek-v4-flash-vision-exp1.0M$0.22
glm-5.3-flash1.0M$0.15
glm-5.31.0M$1.40
nemotron-lightning-3.5-30b-a3b262K$0.05
deepseek-v4-pro-08131M$1.32
muse-glimmer-30b131K$0.35
qwen3.8-max1M$2.00

call gpt-oss-20b through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

gpt-oss-20bfireworks aiin $0.07 /1Mout $0.30 /1Mctx 131Khosted US2 providers serve this model