Model Cataloggroq

GPT-OSS 20B

openai/gpt-oss-20b

CHAT Light tier Reasoning Open-weight

GPT-OSS 20B (openai/gpt-oss-20b) is a chat model from groq with a 131.1K-token context window; open-weight (21B parameters); capabilities tools, reasoning; input text.

131.1KContext
32.8KMax output
$0.075$ / 1M in
14.9Intelligence
243.28tok / s

Pricing

Input
$0.075 / 1M tokens
Output
$0.3 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.

Benchmarks

Intelligence index
14.9
Coding
20.7
Math
89.3

Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.

Performance

Throughput
243.28 tokens/s
Latency (TTFT)
0.405 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.

Specifications

Context window
131,072 tokens (131.1K)
Max output
32,768 tokens
Weights
Open-weight
Parameters
21B
Input modalities
text

Capabilities

tools reasoning

Provenance

artificial-analysiscommittedlitellmoverrides
Last verified: 2026-07-22

Related models

Kimi K2 Instruct
moonshotai/kimi-k2-instruct-0905
groq · CHAT · 262.1K ctx
GPT-OSS 120B
openai/gpt-oss-120b
groq · CHAT · 131.1K ctx
Llama 4 Maverick 17B
meta-llama/llama-4-maverick-17b-128e-instruct
groq · CHAT · 131.1K ctx
Llama 4 Scout 17B
meta-llama/llama-4-scout-17b-16e-instruct
groq · CHAT · 131.1K ctx
Qwen3 32B
qwen/qwen3-32b
groq · CHAT · 131K ctx
Llama 3.1 8B Instant
llama-3.1-8b-instant
groq · CHAT · 128K ctx