Llama 3.3 70B Instruct vs GPT-OSS 120B
meta-llama/llama-3.3-70b-instruct · openai/gpt-oss-120b
As of October 31, 2026, GPT-OSS 120B is the cheaper API on UberLLM: $0.0001 per million input tokens and $0.0006 per million output, versus $0.0479 / $0.1533 for Llama 3.3 70B Instruct, about 100% less when output is 3 tokens for every input token. These are the median prices buyers paid over the last 24 hours. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose GPT-OSS 120B to cut cost; choose Llama 3.3 70B Instruct when its capabilities fit your task better.
Llama 3.3 70B Instruct vs GPT-OSS 120B, side by side
| Spec | Llama 3.3 70B Instruct | GPT-OSS 120B |
|---|---|---|
| Price · input / 1M | $0.0479 | $0.0001 |
| Price · output / 1M | $0.1533 | $0.0006 |
| Context length | 128,000 | 128,000 |
| Max output tokens | 4,096 | 16,384 |
| Input modalities | text | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| % off list | 52% off | 99.8% off |
Median prices buyers paid on UberLLM over the last 24 hours. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated October 31, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Llama 3.3 70B Instruct vs GPT-OSS 120B — FAQ
Is Llama 3.3 70B Instruct or GPT-OSS 120B cheaper?
GPT-OSS 120B is cheaper on a blended token mix, by about 100%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between Llama 3.3 70B Instruct and GPT-OSS 120B?
Llama 3.3 70B Instruct: $0.0479 in / $0.1533 out per 1M tokens. GPT-OSS 120B: $0.0001 in / $0.0006 out per 1M tokens. That's roughly a 100% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Llama 3.3 70B Instruct and GPT-OSS 120B with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.