How much does the gpt-oss-120b API cost?

On FastMetal, gpt-oss-120b is billed per token: $0.102 per 1M input tokens and $0.5035 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call gpt-oss-120b with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-oss-120b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of gpt-oss-120b?

131,072 tokens, shared between the prompt and the response.

How does gpt-oss-120b rank?

#155 on the public arena's Japanese board (ELO 1,325). Ranks move as the leaderboard is updated.

What do I need to try gpt-oss-120b?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

gpt-oss-120b API — pricing, context window, how to use

Back to Models

OpenAI

gpt-oss-120b

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

8/5/2025

131,072 tokens

#155 Text (Japanese)

Input: $0.102/M

Output: $0.5035/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

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_k

top_logprobs

top_p

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.1s

Throughput (p50)327 tokens/s

Measured through FastMetal's own gateway over the last 30 days (661 first-response samples).

Throughput is sampled once a day: the median of 26 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How gpt-oss-120b actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

**Step‑by‑step count of the letter “r” in the word “strawberry”** 1. Write out the word with each letter in order, labeling its position: | Position | Letter | |----------|--------| | 1 | s | | 2 | t | | 3 | **r** | | 4 | a | | 5 | w | | 6 | b | | 7 | e | | 8 | **r** | | 9 | **r** | |10 | y | 2. Scan the list and mark every occurrence of the letter **r**. - Position 3 → r (first occurrence) - Position 8 → r (second occurrence) - Position 9 → r (third occurrence) 3. Count the marked entries: there are **3** marked positions. **Result:** The word “strawberry” contains **3** occurrences of the letter **r**…

1.7s response332 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

### Why the `map` can’t be called `Array.prototype.map` is a method that exists only on **arrays** (or array‑like objects). When you see ``` TypeError: Cannot read properties of undefined (reading 'map') at UserList (...) ``` it means that the variable you think is an array – `users` in this case – is actually **`undefined`** (or `null`). React is trying to evaluate this line: ```jsx {users.map(user => <li key={user.id}>{user.name}</li>)} ``` and it crashes because you can’t read `.map` from `undefined`. --- ## Common reasons `users` ends up undefined | Reason | Typical scenario | How it shows up | |--------|------------------|-----------------| | **Prop not passed** | `<Use…

7.3s response1610 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

Below is a **step‑by‑step review** of the original `get_data` implementation followed by a **refactored version** that addresses readability, performance, and modern Python best‑practice concerns. --- ## 1. What the original function does ```python def get_data(url, retries=3): import requests import time for i in range(retries): try: r = requests.get(url, timeout=10) if r.status_code == 200: data = r.json() result = [] for item in data: if item["active"] == True: result.append({"name": item["name"], "id": item["id"]}) return result…

14.4s response3132 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the gpt-oss-120b API cost?: On FastMetal, gpt-oss-120b is billed per token: $0.102 per 1M input tokens and $0.5035 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call gpt-oss-120b with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "gpt-oss-120b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of gpt-oss-120b?: 131,072 tokens, shared between the prompt and the response.
How does gpt-oss-120b rank?: #155 on the public arena's Japanese board (ELO 1,325). Ranks move as the leaderboard is updated.
What do I need to try gpt-oss-120b?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try gpt-oss-120b right now

gpt-oss-120b is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

Leaderboard

Text

spanishELO: 1,369

#191

russianELO: 1,337

#219

CodingELO: 1,389

#225

MathELO: 1,381

#190

Creative WritingELO: 1,279

#268

Instruction FollowingELO: 1,324

#235

Hard PromptsELO: 1,362

#225

Multi-TurnELO: 1,327

#241

OverallELO: 1,352

#218

JapaneseELO: 1,325

#155

ChineseELO: 1,377

#215

KoreanELO: 1,267

#210

EnglishELO: 1,361

#231

frenchELO: 1,355

#208

germanELO: 1,328

#195

Rankings: LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, snapshot 2026-10-22; category names mapped and ratings rounded by FastMetal.