gpt-oss-120b (batch)
by OpenAI · openai/gpt-oss-120b:batch · #22 cheapest of 457 paid models
Prices updated Nov 18, 2026, 12:15 PM UTC · refreshed nightly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.03
per 1M tokens
Output
$0.136
per 1M tokens
Blended (3:1)
$0.056
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for gpt-oss-120b (batch) (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.056 | $0.003155 | — |
| 50% | $0.056 | $0.003155 | −0% |
| 90% | $0.056 | $0.003155 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $5.56e-5 | $0.0556 |
| Document summary | 8,000 | 1,000 | $0.000373 | $0.3728 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00116 | $1.16 |
| Long-context analysis | 150,000 | 5,000 | $0.00512 | $5.12 |
Performance
Intelligence Index
3.8
AA composite quality
Coding Index
30.4
Math Index
—
Agentic Index
3.7
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 959 |
| UI components | 915 |
| Data viz | 984 |
| 3D | 881 |
| Game dev | 981 |
| Code categories | 951 |
Specs
Context window
131K
tokens
Max output
118K
tokens
Input modalities
text
Tokenizer
GPT