gpt-oss-120b
OpenAIdevelopers.openai.com/api/docs/models/gpt-oss-12
Most powerful open-weight model, fits into an H100 GPU
Updated 37 min ago · first seen 11 Sept 2026
model_01M293VC69K5D58EP5QCDWXVWY
- Parameters
- 116.8B
- T2 · 40 min ago
- Context
- 131.1K tokens
- T2 · 41 min ago
- Released
- 5 Aug 2025
- T2 · 41 min ago
- Knowledge cutoff
- Jun 2024
- T2 · 41 min ago
Specification
- Release date
- 5 Aug 2025
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Openness
- open-weights
Source:OpenAI Platform docsT1observed 1 h agohigh
- Parameters
- 116.8B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 40 min agomedium
- Context window
- 131.1K tokens
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Max output
- 118K tokens
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Knowledge cutoff
- Jun 2024
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Tokenizer
- GPT
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- API model id
- gpt-oss-120b
Source:OpenAI Platform docsT1observed 1 h agohigh
- Hugging Face repo
- openai/gpt-oss-120b
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 40 min agomedium
- Official page
Source:OpenAI Platform docsT1observed 1 h agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 40 min agomedium
- Downloads
- 5,463,732
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 37 min agomedium
- Likes
- 5,188
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 37 min agomedium
- Groq model id
- openai/gpt-oss-120b
Source:Groq — docs & pricingT1observed 41 min agohigh
- Last modified
- 2025-08-26T17:25:03+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 40 min agomedium
- Openrouter id
- openai/gpt-oss-120b
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Supported 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
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
25
Source tiers
T1T25 / 20
Freshest observation
37 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 131.1K tokens
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Max output
- 118K tokens
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Knowledge cutoff
- Jun 2024
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
- Tokenizer
- GPT
Source:OpenRouter public model & pricing listingT2observed 41 min agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenAI APIopenai/gpt-oss-120b | $0.037 | $0.17 | — | — | 131.1K | 41 min ago | openrouter.aiT2 |
| Fireworks AIfireworks/gpt-oss-120b | $0.15 | $0.60 | $0.015 | — | — | 51 min ago | app.fireworks.aiT1 |
| GroqCloudopenai/gpt-oss-120b | $0.15 | $0.60 | — | — | 131.1K | 41 min ago | console.groq.comT1 |
| OpenAI APIopenai/gpt-oss-120b:batch | $0.15 | $0.60 | — | — | 131.1K | 41 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 3
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- Fireworks AI
- OpenAI API
- GroqCloud
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 67.7 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 67.7 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 67.7 GB | Yes |
| Apple M2 Ultra | 4bit | — | 67.7 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 67.7 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 67.7 GB | Yes |
| Apple M1 Ultra | 4bit | — | 67.7 GB | Yes |
| Apple M3 Max | 4bit | — | 67.7 GB | Yes |
| Apple M4 Max | 4bit | — | 67.7 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 67.7 GB | Yes |
| Apple M2 Max | 4bit | — | 67.7 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 67.7 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 67.7 GB | Yes |
| Apple M1 Max | 4bit | — | 67.7 GB | No |
| Apple M4 Pro | 4bit | — | 67.7 GB | No |
| Apple M3 Pro | 4bit | — | 67.7 GB | No |
| Apple M1 Pro | 4bit | — | 67.7 GB | No |
| Apple M2 Pro | 4bit | — | 67.7 GB | No |
| Apple M4 | 4bit | — | 67.7 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 67.7 GB | No |
| Apple M2 | 4bit | — | 67.7 GB | No |
| Apple M3 | 4bit | — | 67.7 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 67.7 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 67.7 GB | No |
| Apple M1 | 4bit | — | 67.7 GB | No |
Ancestors 0
None recorded.
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Max output
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 118K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
GroqCloud lists gpt-oss-120b at $0.15 in / $0.6 out per 1M tokens
groq_pricingOpenAI API lists gpt-oss-120b at $0.15 in / $0.6 out per 1M tokens
openrouterOpenAI API lists gpt-oss-120b at $0.037 in / $0.17 out per 1M tokens
openrouterFireworks AI lists gpt-oss-120b at $0.15 in / $0.6 out per 1M tokens
fireworks_pricing
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Groq — docs & pricing | console.groq.com/docs/models | model_docs | T1· Official | 39 min ago | 1 |
| Fireworks AI — pricing | docs.fireworks.ai/serverless/pricing.md | pricing | T1· Official | 46 min ago | 1 |
| OpenAI Platform docs | developers.openai.com/api/docs/models.md | model_docs | T1· Official | 49 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/amd/gpt-oss-120b-w-mxfp4-a-fp8 | model_page | T2· Quality secondary | 31 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=openai&p=0&sort=downloads | listing | T2· Quality secondary | 37 min ago | 2 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 41 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.