GPT OSS 120B
openai/gpt-oss-120bVon OpenAI · Familie: gpt-oss · veröffentlicht 2025-08-05 · Wissensstand: 2025-08
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Fähigkeiten
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding82
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)2/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output100
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume20/20
Cost efficiency79
- Headline price (log-scaled)79/95
- Has prompt-cache pricing0/5
Long context46
- Context window (100K → 2M)36/90
- Has published price for full window10/10
Production-readiness94
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.28 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $0.56 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.16 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $0.48 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $0.58 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Preis-Details
Empfohlene Preise von helicone · gpt-oss-120b
Günstigster Anbieter: nvidia · Unknown Eingabe + Unknown Ausgabe
Bei 33 Anbietern verfügbar
| Anbieter | Anbieter-Modell-ID | Eingabe / 1M | Ausgabe / 1M | Kontext | Veröffentlicht |
|---|---|---|---|---|---|
| OpenRouter openrouter | openai/gpt-oss-120b | $0.072 | $0.280 | 131K | 2025-08-05 |
| Vercel AI Gateway vercel | openai/gpt-oss-120b | $0.100 | $0.500 | 131K | 2025-08-05 |
| Groq groq | openai/gpt-oss-120b | $0.150 | $0.600 | 131K | 2025-08-05 |
| Together AI togetherai | openai/gpt-oss-120b | $0.150 | $0.600 | 131K | 2025-08-05 |
| Deep Infra deepinfra | openai/gpt-oss-120b | $0.050 | $0.240 | 131K | 2025-08-05 |
| Scaleway scaleway | gpt-oss-120b | $0.150 | $0.600 | 128K | 2024-01-01 |
| NanoGPT nano-gpt | TEE/gpt-oss-120b | $2.00 | $2.00 | 131K | 2025-08-05 |
| NanoGPT nano-gpt | openai/gpt-oss-120b | $0.050 | $0.250 | 128K | 2025-08-05 |
| Abacus abacus | openai/gpt-oss-120b | $0.080 | $0.440 | 128K | 2025-08-05 |
| submodel submodel | openai/gpt-oss-120b | $0.100 | $0.500 | 131K | 2025-08-23 |
| IO.NET io-net | openai/gpt-oss-120b | $0.040 | $0.400 | 131K | 2024-12-01 |
| NovitaAI novita-ai | openai/gpt-oss-120b | $0.050 | $0.250 | 131K | 2025-08-06 |
| Weights & Biases wandb | openai/gpt-oss-120b | $0.150 | $0.600 | 131K | 2025-08-05 |
| Qiniu qiniu-ai | gpt-oss-120b | Unknown | Unknown | 128K | 2025-08-06 |
| Kilo Gateway kilo | openai/gpt-oss-120b | $0.039 | $0.190 | 131K | 2025-08-05 |
| Cloudflare AI Gateway cloudflare-ai-gateway | workers-ai/@cf/openai/gpt-oss-120b | $0.350 | $0.750 | 128K | 2025-08-05 |
| Nebius Token Factory nebius | openai/gpt-oss-120b | $0.150 | $0.600 | 128K | 2026-01-10 |
| Helicone helicone | gpt-oss-120b | $0.040 | $0.160 | 131K | 2024-06-01 |
| Ollama Cloud ollama-cloud | gpt-oss:120b | Unknown | Unknown | 131K | 2025-08-05 |
| Baseten baseten | openai/gpt-oss-120b | $0.100 | $0.500 | 128K | 2025-08-05 |
| Venice AI venice | openai-gpt-oss-120b | $0.070 | $0.300 | 128K | 2025-11-06 |
| CloudFerro Sherlock cloudferro-sherlock | openai/gpt-oss-120b | $2.92 | $2.92 | 131K | 2025-08-28 |
| evroc evroc | openai/gpt-oss-120b | $0.240 | $0.940 | 66K | 2025-08-05 |
| Nvidia nvidia | openai/gpt-oss-120b | Unknown | Unknown | 128K | 2025-08-04 |
| DigitalOcean digitalocean | openai-gpt-oss-120b | $0.100 | $0.700 | 131K | 2025-08-05 |
| OVHcloud AI Endpoints ovhcloud | gpt-oss-120b | $0.090 | $0.470 | 131K | 2025-08-28 |
| SiliconFlow siliconflow | openai/gpt-oss-120b | $0.050 | $0.450 | 131K | 2025-08-13 |
| Cloudflare Workers AI cloudflare-workers-ai | @cf/openai/gpt-oss-120b | $0.350 | $0.750 | 128K | 2025-08-05 |
| FastRouter fastrouter | openai/gpt-oss-120b | $0.150 | $0.600 | 131K | 2025-08-05 |
| STACKIT stackit | openai/gpt-oss-120b | $0.490 | $0.710 | 131K | 2025-08-05 |
| Privatemode AI privatemode-ai | gpt-oss-120b | Unknown | Unknown | 128K | 2025-08-04 |
| Berget.AI berget | openai/gpt-oss-120b | $0.440 | $0.990 | 128K | 2025-08-05 |
| Regolo AI regolo-ai | gpt-oss-120b | $1.00 | $4.20 | 128K | 2025-08-05 |
Datenunterschiede zwischen Anbietern
- context_window varies: 128000, 131000, 131072, 65536
- release_date varies (span 740d): 2024-01-01, 2024-06-01, 2024-12-01, 2025-08-04, 2025-08-05, 2025-08-06, 2025-08-13, 2025-08-23, 2025-08-28, 2025-11-06, 2026-01-10
- modalities varies across offerings
Anbieter melden unterschiedliche Werte für dieses Modell. Die Schnellinfos oben nutzen den repräsentativen Anbieter; pro Anbieter siehe Tabelle.
Frequently asked questions
How much does GPT OSS 120B cost?
GPT OSS 120B costs $0.040 per 1M input tokens and $0.160 per 1M output tokens, sourced from helicone. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of GPT OSS 120B?
GPT OSS 120B has a context window of 131K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.
Does GPT OSS 120B support tool calling?
Yes. GPT OSS 120B supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does GPT OSS 120B support structured output / JSON mode?
Yes. GPT OSS 120B supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can GPT OSS 120B accept image input?
No. GPT OSS 120B only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is GPT OSS 120B open-weight?
Yes. GPT OSS 120B's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to GPT OSS 120B?
If GPT OSS 120B doesn't fit, consider GPT OSS 20B, GPT-5.2, GPT-5 Mini. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More OpenAI models
- GPT OSS 20B$0.03 in / $0.14 out
- GPT-5.2$1.75 in / $14.00 out
- GPT-5 Mini$0.25 in / $2.00 out
- GPT-5$1.25 in / $10.00 out
- GPT-5.1$1.25 in / $10.00 out
Capability lists this model is in
Zuletzt aktualisiert:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.