← Back to all pricing

GPT-OSS 120B (Cerebras) API Pricing — $0.35/M input, $0.75/M output

Open-weight MoE flagship at ~5,000+ chars/s throughput.

Input
$0.35/M
Output
$0.75/M
Blended
$0.45/M
Provider
Verified 2026-06-14 — source

Speed

Tokens / sec
2450
TTFT
90 ms
Rank
#1 of 31
$ / M ÷ t/s
$0.0002
Measured with 5 runs on a fixed prompt — see the full methodology.

Cost at scale

Tokens / monthEst. cost (blended 3:1)
100,000$0.04
1,000,000$0.45
10,000,000$4.50
100,000,000$45.00

How GPT-OSS 120B (Cerebras) compares

GLM 4.7 (Cerebras) — $2.38/MCodestral — $0.45/MGPT-5.6 Luna — $0.45/MGPT-5.4 Nano — $0.46/M
See all Cerebras models →

FAQ

Is GPT-OSS 120B (Cerebras) cheaper than Codestral?

GPT-OSS 120B (Cerebras) costs $0.45/M blended tokens, Codestral costs $0.45/M — Codestral is cheaper.

How much does 1 million tokens cost with GPT-OSS 120B (Cerebras)?

At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.45. Pure input costs $0.35/M; pure output costs $0.75/M.

Who provides GPT-OSS 120B (Cerebras)?

GPT-OSS 120B (Cerebras) is served by Cerebras. Pricing was last verified on 2026-06-14 against https://www.cerebras.ai/pricing.

Try GPT-OSS 120B (Cerebras) for free

Run real prompts against GPT-OSS 120B (Cerebras) and every other model on this page in one workspace.

Try GPT-OSS 120B (Cerebras) Free