Model Catalogcerebras

GPT-OSS 120B

gpt-oss-120b

CHAT Mid tier Reasoning

GPT-OSS 120B (gpt-oss-120b) is a chat model from cerebras with a 131.1K-token context window; capabilities tools, reasoning; input text.

131.1KContext
32.8KMax output
$0.35$ / 1M in
23.8Intelligence
286.915tok / s

Pricing

Input
$0.35 / 1M tokens
Output
$0.75 / 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
23.8
Coding
30.4
Math
93.4

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

Performance

Throughput
286.915 tokens/s
Latency (TTFT)
0.506 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
Input modalities
text

Capabilities

tools reasoning

Provenance

artificial-analysiscommittedlitellmoverrides
Last verified: 2026-07-22

Related models

GLM-4.6
zai-glm-4.6
cerebras · CHAT · 128K ctx
Llama 3.1 8B
llama3.1-8b
cerebras · CHAT · 128K ctx
Llama 3.3 70B
llama-3.3-70b
cerebras · CHAT · 128K ctx
Qwen3 32B
qwen-3-32b
cerebras · CHAT · 128K ctx