GPT-OSS 120B vs Qwen3-32B
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Groq
3 providers:
Fireworks $0.150/$0.600
Groq $0.150/$0.600
Together $0.150/$0.600
|
by Groq
3 providers:
Alibaba $0.160/$0.640
Groq $0.290/$0.590
DeepInfra $0.080/$0.280
|
|---|---|---|
| Overview | ||
| Status | Current fast Open weights | Current fast Open weights |
| Released | Jan 1, 2026 | Jan 1, 2026 |
| Pricing per million tokens | ||
| Input | $0.150/Mtok | $0.290/Mtok |
| Output | $0.600/Mtok | $0.590/Mtok |
| Blended avg | $0.262/Mtok | $0.365/Mtok |
| Specifications | ||
| Context window | 131K tokens | 128K tokens |
| Parameters | 120B | 32B |
| Speed (TPS) | 500 tok/s | 662 tok/s |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Vellum LLM Leaderboard / LMSYS Chatbot Arena (UC Berkeley) | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 24.1 | 11.4 |
| AA Agentic Index | 13.4 | 1.8 |
| AA-Omniscience Index (−100–100) | -49.2 | -50.4 |
| LMSYS Chatbot Arena | — | 1347.2 ELO |
| Per-benchmark results published for GPT-OSS 120B only — no independent per-benchmark scores exist for Qwen3-32B yet | ||
| Avg benchmark score | 65.5 | — |
| Perf / dollar | 249.5 | — |
| GPQA Diamond | 80.1 | — |
| LiveCodeBench | 69 | — |
| Humanity's Last Exam | 14.9 | — |
| AIME 2025 | 97.9 | — |
| Providers | ||
| Available from |
Fireworks — $0.150/$0.600/Mtok
Groq — $0.150/$0.600/Mtok
Together — $0.150/$0.600/Mtok
|
Alibaba — $0.160/$0.640/Mtok
Groq — $0.290/$0.590/Mtok
DeepInfra — $0.080/$0.280/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-OSS 120B | Qwen3-32B | Savings |
|---|---|---|---|
| 1M tokens | $0.26 | $0.37 | $0.1 (27.4%) |
| 10M tokens | $2.62 | $3.65 | $1.03 (28.2%) |
| 100M tokens | $26.25 | $36.5 | $10.25 (28.1%) |
| 1000M tokens | $262.5 | $365 | $102.5 (28.1%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.262/Mtok blended vs $0.365 — 28.1% less on the same 50/50 token mix
- latency-sensitive traffic: 662 tok/s measured throughput vs 500
Price movement
recorded changes since we began tracking each model · last checked Aug 22, 2026| Model | Changes | Latest move | Old → new $/M |
|---|---|---|---|
| GPT-OSS 120B | 1 | price cut on Jan 27, 2026 | $0.15/$0.75 → $0.15/$0.6/Mtok |
| Qwen3-32B | 0 | — no move | Stable since we began tracking — no change recorded |
The cheaper option here — GPT-OSS 120B costs $0.262/Mtok blended on Groq.
Summary
GPT-OSS 120B by Groq costs $0.150/Mtok input and $0.600/Mtok output, with a 131K-token context window. It supports text input and is available from 3 providers.
Qwen3-32B by Groq costs $0.290/Mtok input and $0.590/Mtok output, with a 128K-token context window. It supports text input and is available from 3 providers.
On a blended cost basis, GPT-OSS 120B is 28.1% cheaper than Qwen3-32B.It also has a larger context window.
The two aren't directly comparable on average benchmark score: GPT-OSS 120B has published per-benchmark results, while Qwen3-32B does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.