gpt-oss-120b API pricing
$0.20 in, $1.80 out per million tokens.
gpt-oss-120bmanaged routeOpenAI SDK
Price · per million tokens, USD
Get a key| Tokens | OpenAI list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.20 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.80 | — |
No list price on record. Same price on every host.
Real-model check: Same fingerprint since Oct 20
gpt-oss-120b: what it is · from OpenAI’s own model card, read 2026-10-20
OpenAI’s larger open-weight model, for production, general-purpose and high-reasoning work. OpenAI sized it to fit on one 80 GB GPU. It is served as gpt-oss-120b at $0.20 input and $1.80 output per million tokens, on the same key as every other model in the catalog.
| gpt-oss-120b | |
|---|---|
| Developer | OpenAI |
| Parameters | 117B total, 5.1B active per token |
| Context | 131,072 tokens in its config |
| License | Apache-2.0 |
| Published | 2025-08-04 |
| Downloads, 30 days to 2026-10-20 | 3,141,375 |
| Source | openai/gpt-oss-120b |
From openai/gpt-oss-120b, read 2026-10-20.
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"gpt-oss-120b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'gpt-oss-120b next to OpenAI’s other models · per million tokens, live
| Model | Here, in / out | 1,000 chat turns |
|---|---|---|
| GPT-6 Luna | $0.0625 / $0.20 | $0.23 |
| GPT OSS 120B Uncensored | $0.1095 / $0.728 | $0.58 |
| GPT-5.6 Luna | $0.12 / $0.72 | $0.60 |
| gpt-oss-20b | $0.16 / $0.72 | $0.68 |
| GPT-4o mini | $0.30 / $1.20 | $1.20 |
| gpt-oss-120b | $0.20 / $1.80 | $1.30 |
| GPT-6 Sol | $0.60 / $3.00 | $2.70 |
| GPT-6.1 Sol | $0.60 / $3.00 | $2.70 |
| GPT-5.6 Sol | $1.20 / $3.00 | $3.90 |
| GPT-5.6 Terra | $1.20 / $3.60 | $4.20 |
| GPT-5.4 Mini | $0.9375 / $5.625 | $4.69 |
| GPT-5.5 | $1.80 / $9.00 | $8.10 |
| GPT-6 Astra | $3.00 / $15.00 | $13.50 |
| GPT-5.4 | $3.125 / $18.75 | $15.63 |
| GPT-4o | $5.00 / $20.00 | $20.00 |
| GPT-5.3-Codex | $3.50 / $28.00 | $21.00 |
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for gpt-oss-120b: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.20 input and $1.80 output per million tokens, that is $0.40 + $0.90 = $1.30, paid from prepaid credit with no subscription.
gpt-oss-120b API · base URL and key
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'gpt-oss-120b',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from OpenAI
gpt-oss-120b questions
- What is gpt-oss-120b?
- gpt-oss-120b is a model from OpenAI. Through UplinkSwitch it answers the OpenAI SDK on one key as gpt-oss-120b.
- How much does the gpt-oss-120b API cost?
- $0.20 per million input tokens and $1.80 per million output tokens.
- Is gpt-oss-120b free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0011.
- What is the gpt-oss-120b model id?
- gpt-oss-120b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a gpt-oss-120b API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls gpt-oss-120b and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real gpt-oss-120b?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. gpt-oss-120b's latest result: Same fingerprint since Oct 20.
- Is there a gpt-oss-120b API?
- Yes: gpt-oss-120b on the OpenAI format at https://api.uplinkswitch.com/v1, $0.20 input and $1.80 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
- How many parameters does gpt-oss-120b have?
- 117B total, 5.1B active per token, per openai/gpt-oss-120b.
- What is gpt-oss-120b's context window?
- 131,072 tokens in its config, per openai/gpt-oss-120b.
- Is gpt-oss-120b open source?
- Its weights are open on Hugging Face (openai/gpt-oss-120b); the license is Apache-2.0.
- What does gpt-oss-120b cost per 100 messages?
- $0.13 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.20 input and $1.80 output per million tokens, from prepaid credit with no subscription.
- gpt-oss-120b or gpt-oss-20b?
- gpt-oss-120b is for quality and harder reasoning; gpt-oss-20b is for lower latency at a lower price. gpt-oss-120b is $0.20 / $1.80 per million tokens in / out, $1.30 for 1,000 chat turns; gpt-oss-20b is $0.16 / $0.72 per million tokens in / out, $0.68 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.