OpenAI: gpt-oss-120b
Catalog snapshot on AI Hippo. This model is discoverable on-site even when it is not currently included in the global ranking list.
Data updated:
Model
6 verified sources
Aggregator quote only — no official sync yet
Next steps on AI Hippo
Open weights snapshot
openai/gpt-oss-120b
Task text-generation
- Downloads
- 4.4M
- Likes
- 5.0k
- Parameters
- 0B
90d download trend
This model is currently available from the catalog snapshot and may not be included in the latest ranked board yet.
About this model
OpenAI: gpt-oss-120b is listed in our model catalog as a LLM model with 131,072 ctx and a snapshot average price around $0.10 per 1M tokens. The tables below summarize the latest catalog snapshot; use Compare or the Token hub to dig deeper.
You can also explore more models from OpenAI , and browse more options from 🇺🇸 United States .
Capabilities & specs
- Modality
- text->text
- Input modalities
- text
- Knowledge cutoff
- 2024-06-30
- Supported API parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_a, top_k, top_logprobs, top_p
Catalog description: 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...
Token pricing by provider
Compare per-provider token prices for this model across available platforms.
| Provider | Input / 1M tokens | Output / 1M tokens | Latency | Status |
|---|---|---|---|---|
| AWS Bedrock | $0.15 | $0.60 | — | Verified · 2026-08-02 |
| Fireworks | $0.15 | $0.60 | — | Verified · 2026-08-02 |
| Groq | $0.15 | $0.60 | — | Verified · 2026-08-02 |
| OpenRouter | $0.04 | $0.17 | — | Verified · 2026-08-02 |
| SiliconFlow | $0.05 | $0.45 | — | Verified · 2026-08-02 |
| Together | $0.15 | $0.60 | — | Verified · 2026-08-02 |
Provider prices are sourced from the token comparison dataset and may change between snapshots.
Alternative picks
-
Meituan: LongCat 2.0
Compare now -
DeepSeek V4 Flash Latest
Compare now -
DeepSeek: DeepSeek V4 Flash 0731
Compare now
Pick one or two more models on global rankings and use Compare to view them side by side.
FAQ
Why is the official price missing?
Official rows require a verified direct vendor or cloud API price. When only aggregators list a model, the Official column shows — and verified aggregator quotes appear in the token table.
How is context different from max output tokens?
Context window is how much input the model can accept in a single request. Max output tokens is the per-response generation cap from the primary listing—often much smaller than the context window.
Where do multi-provider prices come from?
Prices are crawled or synced from token providers (OpenRouter, Groq, Together, and others) and merged into the infrastructure comparison dataset. Verified rows show a fetch date in the status column.
Data source & methodology
- Source
- OpenRouter catalog, verified vendor crawls, and Hugging Face hub snapshots.
- Metrics
- Context window, blended 1M-token price, max output tokens, and capability fields from the OpenRouter models API.
- Update cadence
- Daily pipeline refresh; provider prices may change between snapshots.
- Fetched at
- 2026-08-02
- Method
- Composite rank uses on-site context × price weighting (not LMSYS Arena ELO).