Find a model

Browse the full catalog →

Gemma 4 31B vs Ministral 3 3B 2512

Practical read: Gemma 4 31B reads two times more context and starts answering sooner. Ministral 3 3B 2512 costs about half as much. One API key runs both.

No card required. Start with 1 million free tokens.

Side by side:

Google: Gemma 4 31B compared with Mistral: Ministral 3 3B 2512
Attribute Gemma 4 31B google/gemma-4-31b-it Ministral 3 3B 2512 mistralai/ministral-3b-2512
Price, 1M in + out $0.46 Weights & Biases, cheapest route $0.21 Mistral, cheapest route
Best for Long documents and speed Low cost
Input / output, 1M $0.11 / $0.36 $0.11 / $0.11
Cached input $0.060927/1M to $0.26375/1M $0.01055/1M
Context window 262K 262,144 tokens 131K 131,072 tokens
First token, p50 0.70 s via Sail Research 0.81 s via Mistral
Throughput 198 tok/s via SambaNova Measuring
AI IQ IQ 101 #130 on AI IQ Unrated
Provider routes 15 with failover 1
Privacy Confidential E2EE and zero retention route Varies by provider
Recent route uptime range 96.43% to 100.00% 100.00%
Publisher Google AI Studio Mistral
Modes chat chat
More detail

Price adds one million input and one million output tokens on the cheapest route. Prices and speed change: see the monthly reports and run a small eval before you choose a default.

Test both with your agent

Paste this into Claude Code, Cursor or any coding agent.

Compare Gemma 4 31B and Ministral 3 3B 2512 in this project through TrustedRouter.

1. Read https://trustedrouter.com/docs/llms.txt
2. Point the OpenAI-compatible client at
   https://api.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Run our eval prompts on google/gemma-4-31b-it, then on mistralai/ministral-3b-2512.
4. Show me cost, latency and quality side by side before changing the default.
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
for model in ("google/gemma-4-31b-it", "mistralai/ministral-3b-2512"):
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "What is the capital of France?"}],
    )
    print(model, response.choices[0].message.content)
for model in google/gemma-4-31b-it mistralai/ministral-3b-2512; do
  curl https://api.trustedrouter.com/v1/chat/completions \
    -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
    -H "Content-Type: application/json" \
    -d "{\"model\": \"$model\", \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]}"
done
Your agent will need an API key.

Questions

Which should I use, Google: Gemma 4 31B or Mistral: Ministral 3 3B 2512?

Google: Gemma 4 31B has more Credits provider routes, the larger context window and the lower measured p50 time to first token. Ministral 3 3B 2512 has the lower published input-plus-output rate.

Is Google: Gemma 4 31B or Mistral: Ministral 3 3B 2512 cheaper?

The current cheapest TrustedRouter route is $0.4642/1M for Google: Gemma 4 31B and $0.211/1M for Mistral: Ministral 3 3B 2512. The comparison uses current catalog prices and updates as provider pricing changes.

Is Google: Gemma 4 31B or Mistral: Ministral 3 3B 2512 faster?

Current measured p50 time to first token is 701 ms for Google: Gemma 4 31B and 815 ms for Mistral: Ministral 3 3B 2512. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test Google: Gemma 4 31B and Mistral: Ministral 3 3B 2512 with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between google/gemma-4-31b-it and mistralai/ministral-3b-2512. This makes side-by-side evals possible without maintaining two provider integrations.

More comparisons

All comparisons

Try Gemma 4 31B and Ministral 3 3B 2512 with one key.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

No card required. Start with 1 million free tokens.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

By continuing you agree to the terms of service and privacy policy.