Inference & pricing
Model comparison

Vikasit 3 Flash vs gpt-oss-120b

gpt-oss-120b has very low input pricing and more raw capacity; Vikasit 3 Flash is a fast, low-latency small-tier model. Pick gpt-oss-120b for input-heavy or more demanding turns; pick Vikasit 3 Flash for snappy, high-frequency interactions.

Pricing comparison

MetricVikasit 3 Flashgpt-oss-120b
Input ($ / 1M tokens)$0.30$0.05
Output ($ / 1M tokens)$0.96$0.45
Blended (3:1 in:out)$0.46$0.15
OpenAI-compatible APIYesYes

Prices are per 1M tokens in USD. Blended cost assumes a 3:1 input-to-output token ratio, a common pattern for chat and generation workloads. Actual cost depends on your traffic. Vikasit 3 Flash is available through the Vikasit Inference API.

Choose Vikasit 3 Flash when

  • Latency-sensitive, high-frequency requests
  • Short outputs where output price dominates
  • A tuned fast tier that fits your stack

Choose gpt-oss-120b when

  • Input-heavy prompts with short outputs
  • You want more model capacity for harder turns
  • Open-weight footing matters to you

Quick start with Vikasit 3 Flash

Call Vikasit 3 Flash through the OpenAI-compatible Vikasit Inference API at https://api.vikasit.ai/v1. Change two lines in your existing OpenAI code — the base URL and your key.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.vikasit.ai/v1",
    api_key="sk-vikasit-...",
)

resp = client.chat.completions.create(
    model="vikasit-3-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

FAQ

Is Vikasit 3 Flash cheaper than gpt-oss-120b?

Per 1M tokens, Vikasit 3 Flash costs $0.30 input / $0.96 output, while gpt-oss-120b costs $0.05 input / $0.45 output. On output tokens — which usually dominate generation cost — gpt-oss-120b is the cheaper option.

Can I call Vikasit 3 Flash with the OpenAI SDK?

Yes. The Vikasit Inference API is OpenAI-compatible. Point any OpenAI SDK at https://api.vikasit.ai/v1 with your Vikasit API key and set the model id — chat completions, streaming, and tool calls all work.

Should I choose Vikasit 3 Flash or gpt-oss-120b?

gpt-oss-120b has very low input pricing and more raw capacity; Vikasit 3 Flash is a fast, low-latency small-tier model. Pick gpt-oss-120b for input-heavy or more demanding turns; pick Vikasit 3 Flash for snappy, high-frequency interactions.

Start with Vikasit 3 Flash

Get an API key and 2M free tokens a day on Vikasit Nova. Pay-as-you-go, no minimums, OpenAI-compatible.