Neither wins outright: IBM: Granite 4.2 8B is the pick when cost matters at scale, OpenAI: gpt-oss-120b when you want to prototype at zero cost.
| Spec | IBM: Granite 4.2 8B | OpenAI: gpt-oss-120b |
|---|---|---|
| Provider | Ibm Granite | OpenAI |
| Input price (per 1M tokens) | $0.06 | $0.15 |
| Output price (per 1M tokens) | $0.25 | $0.60 |
| Blended price (3:1 input/output) | $0.11 | $0.26 |
| Cheaper than … of all models we track | 79% | 64% |
| Context window | 131K tokens (~197 pages) | 131K tokens (~197 pages) |
| Larger context than … of all models | 23% | 23% |
| Max output per response | 118K tokens (~88,500 words) | 66K tokens (~49,200 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | Yes |
| Listed since | 2026-08-31 | 2025-08-05 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | IBM: Granite 4.2 8B | OpenAI: gpt-oss-120b | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $9.50 | $23.25 | IBM: Granite 4.2 8B saves $13.75 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $9.70 | $24.00 | IBM: Granite 4.2 8B saves $14.30 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $10.20 | $25.20 | IBM: Granite 4.2 8B saves $15.00 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $6.30 | $15.60 | IBM: Granite 4.2 8B saves $9.30 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $3.25 | $8.10 | IBM: Granite 4.2 8B saves $4.85 |
| Capability | IBM: Granite 4.2 8B | OpenAI: gpt-oss-120b | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | — | — | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | ✓ Yes | ✓ Yes | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-10-13 | OpenAI: gpt-oss-120b | $0.15 | $0.60 |
| 2026-09-30 | OpenAI: gpt-oss-120b | $0.04 | $0.17 |
| 2026-09-22 | IBM: Granite 4.2 8B | $0.06 | $0.25 |
| 2026-09-21 | IBM: Granite 4.2 8B | $0.10 | $0.15 |
| 2026-09-18 | OpenAI: gpt-oss-120b | $0.15 | $0.60 |
| 2026-09-09 | IBM: Granite 4.2 8B | $0.06 | $0.25 |
| 2026-08-23 | OpenAI: gpt-oss-120b | $0.04 | $0.17 |
| 2026-08-12 | OpenAI: gpt-oss-120b | $0.03 | $0.17 |
Neither wins outright: IBM: Granite 4.2 8B is the pick when cost matters at scale, OpenAI: gpt-oss-120b when you want to prototype at zero cost. In short: IBM: Granite 4.2 8B when cost matters at scale, you generate long outputs in one go, you want the newer model; OpenAI: gpt-oss-120b when you want to prototype at zero cost.
IBM: Granite 4.2 8B is cheaper: $0.11 vs $0.26 per 1M tokens at a typical 3:1 input/output mix, 59% less. For 50,000 support conversations a month that is $9.50 against $23.25.
IBM: Granite 4.2 8B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens; OpenAI: gpt-oss-120b costs $0.15 input and $0.60 output. Output tokens are billed separately, so long answers shift the gap.
Both take 131K tokens per request — roughly 197 pages of text.
Tool calling — IBM: Granite 4.2 8B: yes, OpenAI: gpt-oss-120b: yes. JSON-schema structured output — IBM: Granite 4.2 8B: yes, OpenAI: gpt-oss-120b: yes.
Neither accepts image input — both are text-in models.
OpenAI: gpt-oss-120b has a free variant (openai/gpt-oss-120b:free). Free variants usually carry tighter rate limits.
IBM: Granite 4.2 8B can write up to 118K tokens (about 88,500 words) per response; OpenAI: gpt-oss-120b up to 66K (about 49,200 words).
IBM: Granite 4.2 8B was listed on 2026-08-31; OpenAI: gpt-oss-120b on 2025-08-05.
IBM: Granite 4.2 8B: input price cut 40% ($0.10 → $0.06/1M), output price raised 40% ($0.15 → $0.25/1M) on 2026-09-22 (3 price changes since 2026-09-01). OpenAI: gpt-oss-120b: input price raised 75% ($0.04 → $0.15/1M), output price raised 72% ($0.17 → $0.60/1M) on 2026-10-13 (6 price changes since 2026-03-10).
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Full IBM: Granite 4.2 8B specs →gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Full OpenAI: gpt-oss-120b specs →