Neither wins outright: OpenAI: gpt-oss-120b (batch) is the pick when cost matters at scale, Qwen: Qwen3 VL 8B Thinking when you need image input.
| Spec | OpenAI: gpt-oss-120b (batch) | Qwen: Qwen3 VL 8B Thinking |
|---|---|---|
| Provider | OpenAI | Qwen |
| Input price (per 1M tokens) | $0.03 | $0.18 |
| Output price (per 1M tokens) | $0.14 | $2.10 |
| Blended price (3:1 input/output) | $0.06 | $0.66 |
| Cheaper than … of all models we track | 87% | 48% |
| 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) | 33K tokens (~24,600 words) |
| Input types | text | image, text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-08-05 | 2025-10-14 |
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) | OpenAI: gpt-oss-120b (batch) | Qwen: Qwen3 VL 8B Thinking | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $4.94 | $55.50 | OpenAI: gpt-oss-120b (batch) saves $50.56 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $4.91 | $42.60 | OpenAI: gpt-oss-120b (batch) saves $37.69 |
| 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) | $5.18 | $46.80 | OpenAI: gpt-oss-120b (batch) saves $41.62 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $3.18 | $27.00 | OpenAI: gpt-oss-120b (batch) saves $23.82 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $1.62 | $11.10 | OpenAI: gpt-oss-120b (batch) saves $9.48 |
| Capability | OpenAI: gpt-oss-120b (batch) | Qwen: Qwen3 VL 8B Thinking | 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 | — | ✓ Yes | 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 | 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 |
|---|---|---|---|
| 2026-09-24 | OpenAI: gpt-oss-120b (batch) | $0.03 | $0.14 |
| 2026-08-06 | Qwen: Qwen3 VL 8B Thinking | $0.18 | $2.10 |
Neither wins outright: OpenAI: gpt-oss-120b (batch) is the pick when cost matters at scale, Qwen: Qwen3 VL 8B Thinking when you need image input. In short: OpenAI: gpt-oss-120b (batch) when cost matters at scale, you generate long outputs in one go; Qwen: Qwen3 VL 8B Thinking when you need image input, you need log-probabilities.
OpenAI: gpt-oss-120b (batch) is cheaper: $0.06 vs $0.66 per 1M tokens at a typical 3:1 input/output mix, 91% less. For 50,000 support conversations a month that is $4.94 against $55.50.
OpenAI: gpt-oss-120b (batch) costs $0.03 per 1M input tokens and $0.14 per 1M output tokens; Qwen: Qwen3 VL 8B Thinking costs $0.18 input and $2.10 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 — OpenAI: gpt-oss-120b (batch): yes, Qwen: Qwen3 VL 8B Thinking: yes. JSON-schema structured output — OpenAI: gpt-oss-120b (batch): yes, Qwen: Qwen3 VL 8B Thinking: yes.
Only Qwen: Qwen3 VL 8B Thinking accepts image input; OpenAI: gpt-oss-120b (batch) is text-only for input.
No free variant is listed for either; both are pay-per-token.
OpenAI: gpt-oss-120b (batch) can write up to 118K tokens (about 88,500 words) per response; Qwen: Qwen3 VL 8B Thinking up to 33K (about 24,600 words).
OpenAI: gpt-oss-120b (batch) was listed on 2025-08-05; Qwen: Qwen3 VL 8B Thinking on 2025-10-14.
OpenAI: gpt-oss-120b (batch): input price cut 80% ($0.15 → $0.03/1M), output price cut 77% ($0.60 → $0.14/1M) on 2026-09-24. Qwen: Qwen3 VL 8B Thinking: input price raised 35% ($0.12 → $0.18/1M), output price raised 35% ($1.36 → $2.10/1M) on 2026-08-06.
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 (batch) specs →Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
Full Qwen: Qwen3 VL 8B Thinking specs →