Gemma 4 31B — pricing & specs
Gemma 4 31B is a fast model from Google, at capability tier 3 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-07-04.
$/M-token pricing
as of 2026-07-04 · OpenRouter (lowest)What Gemma 4 31B costs in practice
At $0.35/M output tokens, Gemma 4 31B is the 3rd-cheapest of 9 priced tier-3 models in the Mintok catalog — about 42% below the tier median of $0.60/M.
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $0.470 |
| A 10K-token request (8K in / 2K out) | $0.0017 |
| 1,000 agent runs (~2K in / 500 out each) | $0.415 |
| 1M-token RAG chat session (900K cached in / 100K out) | $0.116 |
Estimated from list price (as of 2026-07-04) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- Family
- Gemma 4
- Capability tier
- 3 / 8
- Size class
- FAST
- Category
- GENERAL
- Parameters
- 31B total · 31B active (MoE)
- Context window
- 262,144 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference Cerebras Cerebras WSE-3 Turbo at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 3
Same capability tier, sorted by output price — the cheaper-capable options.
- Mistral NeMoMistral$0.15/M out
- Qwen3 32BAlibaba$0.28/M out
- Gemini 2.5 Flash-LiteGoogle$0.40/M out
- Mistral Small 4Mistral$0.60/M out
- Mixtral 8x7BMistral$0.70/M out
- Magistral SmallMistral$1.50/M out
FAQ
How much does Gemma 4 31B cost per token?
Gemma 4 31B costs $0.12 per million input tokens and $0.35 per million output tokens (cached input $0.09/M), via OpenRouter (lowest), as of 2026-07-04.
Is Gemma 4 31B expensive?
At $0.35/M output tokens, Gemma 4 31B is the 3rd-cheapest of 9 priced tier-3 models in the Mintok catalog — about 42% below the tier median of $0.60/M.
What does a typical request with Gemma 4 31B cost?
At list price, a 10K-token request (8K in / 2K out) with Gemma 4 31B costs about $0.0017, and 1,000 agent runs (~2K in / 500 out each) about $0.415.
What is Gemma 4 31B's context window?
Gemma 4 31B supports a 262,144-token context window.
What capability tier is Gemma 4 31B?
Gemma 4 31B sits at capability tier 3 of 8 on the Mintok scale (FAST size class).
Is Gemma 4 31B open-source or proprietary?
Gemma 4 31B is a proprietary model from Google, accessed via API.
Put Gemma 4 31B to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.