Context
131K
Max output
131K
Serving providers
18
Cheapest input
$0.05 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
176 t/s
tokens / second
Time to first token
3.82s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 0% | — | — | |||||||||||||
| APEX Agents | 3% | default | — | |||||||||||||
| CritPt | 1% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 743.8 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 799.3 | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 78% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 18% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 69% | default | — | |||||||||||||
| ||||||||||||||||
| IT-Bench SRE | 6% | default | — | |||||||||||||
| LiveCodeBench | 88% | default | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 51% | default | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 81% | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -50.0 | default | — | |||||||||||||
| ||||||||||||||||
| SciCode | 39% | default | — | |||||||||||||
| ||||||||||||||||
| SWE-bench Pro | 16% | default | — | |||||||||||||
| SWE-bench Verified | 62% | default | — | |||||||||||||
| TerminalBench Hard | 23% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 26% | default | — | |||||||||||||
| ||||||||||||||||
| τ-bench Banking | 12% | default | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 66% | default | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.05 to $3.00 per 1M tokens across 18 providers, so the dearest route costs 5900% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.05 | $0.45 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| NovitaCheapest | $0.05 | $0.25 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Ovhcloud | $0.08 | $0.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Baseten | $0.10 | $0.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Azure | $0.15 | $0.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Fireworks AI | $0.15 | $0.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Groq | $0.15 | $0.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Watsonx | $0.15 | $0.60 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| SambaNova is dearest at $3.00 / $4.50 | ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 67% since first tracked
Cost calculator
estimate your monthly spend on this model$46
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/openai/gpt-oss-120bnovita/openai/gpt-oss-120bovhcloud/gpt-oss-120bbaseten/openai/gpt-oss-120bazure_ai/gpt-oss-120bfireworks_ai/accounts/fireworks/models/gpt-oss-120bgroq/openai/gpt-oss-120bwatsonx/openai/gpt-oss-120btogether_ai/openai/gpt-oss-120btensormesh/openai/gpt-oss-120bscaleway/openai/gpt-oss-120bdatabricks/databricks-gpt-oss-120bopenrouter/openai/gpt-oss-120breplicate/openai/gpt-oss-120bcloudflare/@cf/openai/gpt-oss-120bcerebras/gpt-oss-120bcrusoe/openai/gpt-oss-120bsambanova/gpt-oss-120b
Frequently asked questions
gpt-oss-120b pricing, context and availabilityHow much does gpt-oss-120b cost?
gpt-oss-120b costs $0.05 per 1M input tokens and $0.25 per 1M output tokens at its cheapest provider via DeepInfra. Across 18 serving providers, input prices range from $0.05 to $3.00 per 1M tokens.
What is the context window of gpt-oss-120b?
gpt-oss-120b accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve gpt-oss-120b?
gpt-oss-120b is available from 18 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can gpt-oss-120b do?
gpt-oss-120b supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other OpenAI models
compare pricing across the OpenAI lineupPopular comparisons
head-to-head pages featuring gpt-oss-120b Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI