AiCostCompare

Claude Opus 4.6 vs Gemma 4 31B

Side-by-side API pricing and Artificial Analysis performance for Claude Opus 4.6 (Anthropic) and Gemma 4 31B (Google). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 11:21 AM UTC · refreshed nightly

Claude Opus 4.6

Anthropic

Gemma 4 31B

Google

Pricing
Input $/1M$5.00$0.20
Output $/1M$25.00$0.40
Blended $/1M (3:1)$10.00$0.25
RAG example (30K in / 2K out)$0.2$0.0068
Quality & speed
Intelligence Index—4.4
Coding Index—43.4
Agentic Index—4.2
Output speed (tok/s)——
Time to first token——
Specs
Context window1M262K
Input modalitiestext, image, fileimage, text, video

FAQ

Which is cheaper, Claude Opus 4.6 or Gemma 4 31B?

Gemma 4 31B has the lower blended API price at $0.25 per 1M tokens (3:1 input:output mix), versus $10.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Gemma 4 31B costs about $0.0068 per request versus $0.2. Also compare context windows: Claude Opus 4.6 offers 1M and Gemma 4 31B offers 262K.

Which scores higher on Artificial Analysis benchmarks?

Gemma 4 31B leads on the Artificial Analysis Intelligence Index (4.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.