Gemma 4 31B IT vs Llama 3.3 70B Instruct
google/gemma-4-31b-it · meta-llama/llama-3.3-70b-instruct
As of November 1, 2026, Gemma 4 31B IT is the cheaper API on UberLLM: $0.0012 per million input tokens and $0.0036 per million output, versus $0.0145 / $0.0465 for Llama 3.3 70B Instruct, about 92% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Gemma 4 31B IT to cut cost; choose Llama 3.3 70B Instruct when its capabilities fit your task better.
Gemma 4 31B IT vs Llama 3.3 70B Instruct, side by side
| Spec | Gemma 4 31B IT | Llama 3.3 70B Instruct |
|---|---|---|
| Price · input / 1M | $0.0012 | $0.0145 |
| Price · output / 1M | $0.0036 | $0.0465 |
| Context length | 262,144 | 128,000 |
| Max output tokens | 131,072 | 4,096 |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| % off list | 99% off | 85.5% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 1, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Gemma 4 31B IT vs Llama 3.3 70B Instruct — FAQ
Is Gemma 4 31B IT or Llama 3.3 70B Instruct cheaper?
Gemma 4 31B IT is cheaper on a blended token mix, by about 92%. 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 Gemma 4 31B IT and Llama 3.3 70B Instruct?
Gemma 4 31B IT: $0.0012 in / $0.0036 out per 1M tokens. Llama 3.3 70B Instruct: $0.0145 in / $0.0465 out per 1M tokens. That's roughly a 92% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Gemma 4 31B IT and Llama 3.3 70B Instruct 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.