Theme
Language
Text

GPT-Oss 120B API — how to connect and pay

A high-performance model tuned for a broad range of tasks.

Input ($/1M)
0.0529
Output ($/1M)
0.2429
Context
128K

Prices in $, updated October 25, 2026.

Performance

Last 7 days: responses / client requests that reached a supplier. Retries of one request count once; input checks, disabled routes, and client cancellations do not lower model quality.

Availability

not enough data

not enough data to estimate

Average latency

not enough data

to full response

TTFT

not enough data

to first token

Speed

not enough data

generation speed, tok/s (median)

Strengths

  • OpenAI-compatible access
  • Single key for all models

Good for

  • Chat assistants
  • Automation
  • Text processing
  • Product integration

Capabilities

Context
128K tokens
Max output
32K tokens
Input
text
Tool calling
supported
JSON mode
supported
Vision
no
Reasoning
thinking — Reasoning tokens are billed at the output rate

Open model from OpenAI, very fast on this provider.

Providers

Comparison of public providers for this model: price, availability, TTFT, speed and cache. No measured metrics for these providers yet — showing «—», no invented numbers.

Provider
Defaultdefault
gpt-oss-120b
Input $/1M
0.0529
Output $/1M
0.2429
Context
128K / 32K
Reasoning
thinking
Availability
—
TTFT
—
Speed
—
Cache hit
—
Caching
no

Key facts

The live catalog contains 86 text models.

GPT-Oss 120B: 0.0529 $ input and 0.2429 $ output per 1M tokens.

FAQ about the GPT-Oss 120B API

How much does GPT-Oss 120B cost?

The price of GPT-Oss 120B: $0.0529 per 1M input · $0.2429 per 1M output tokens. Pay only for the tokens you use — no subscriptions or flat fees.

Is it compatible with the OpenAI SDK?

Yes, the API is fully OpenAI-compatible. Just change base_url to https://getvibeapi.com/v1 and set your key — the rest of the code stays the same.

Connect GPT-Oss 120B right now

Sign up in a minute, pay per use, ready-made code above.

Get API key