Claude Opus 4.6 vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview costs less on both: $1.20 in and $7.20 out per million tokens, against $1.50 in and $7.50 out for Claude Opus 4.6. Both on one key at UplinkSwitch, each next to its developer's list price.
Prices · per million tokens, USD
| Tokens | Claude Opus 4.6claude-opus-4-6 | Gemini 3.1 Pro Previewgemini-3.1-pro-preview |
|---|---|---|
| Input | $1.50Anthropic lists $5.00 · 70% under | $1.20Google lists $2.00 · 40% under |
| Cached input | $0.15Anthropic lists $0.50 · 70% under | $0.12Google lists $0.20 · 40% under |
| Output | $7.50Anthropic lists $25.00 · 70% under | $7.20Google lists $12.00 · 40% under |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Max output | 128,000 tokens | 65,536 tokens |
| Input | text, image | text, image, audio, video |
| Released | 2026-02-05 | 2026-02-19 |
| Anthropic lifecycle | active, retires no sooner than 2027-02-05 | — |
| Formats | Anthropic SDK, OpenAI SDK | Gemini SDK, OpenAI SDK |
| Developer | Anthropic |
List price: each developer's published rate, read October 2026. A model with no cached rate bills cached tokens at its input rate. Live from GET https://api.uplinkswitch.com/v1/catalog. Lifecycle from Anthropic's model deprecations, read 2026-10-19.
What the same work costs · USD, here and at list
| Work | Claude Opus 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| 1,000 chat requests | $6.75list $22.50 | $6.00list $10.00 |
| 100 long documents | $9.00list $30.00 | $7.44list $12.40 |
| A month of both, daily | $472.50list $1,575.00 | $403.20list $672.00 |
A chat request is 2,000 input and 500 output tokens; a long document is 50,000 in and 2,000 out; the month is 1,000 chats and 100 documents a day for 30 days, uncached. Over that month Gemini 3.1 Pro Preview costs $69.30 less here.
Newest in the line
- Claude Opus 5.5 is the newest in Claude Opus 4.6's line: $2.10 in and $6.00 out per million tokens here, against $4.00 and $20.00 at list.
Same key, same URL
One base URL and one key serve both models. The request below calls Claude Opus 4.6; put gemini-3.1-pro-preview in the model field to call Gemini 3.1 Pro Preview instead.
shell
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"claude-opus-4-6","messages":[{"role":"user","content":"Hello"}]}'Model pages: Claude Opus 4.6, Gemini 3.1 Pro Preview. Pricing by family: Claude, Gemini. More comparisons: Claude Sonnet 4.6 vs Claude Opus 4.6, Claude Opus 4.6 vs Claude Opus 4.7, GPT-5.4 vs Claude Opus 4.6, Claude Opus 5.5 vs Gemini 3.1 Pro Preview.
Questions
- Which costs less, Claude Opus 4.6 or Gemini 3.1 Pro Preview?
- Gemini 3.1 Pro Preview costs less on both: $1.20 in and $7.20 out per million tokens, against $1.50 in and $7.50 out for Claude Opus 4.6.
- Can I switch between them by changing the model id?
- Yes. Both answer in the OpenAI SDK format at the same base URL with the same key. Change the model id from claude-opus-4-6 to gemini-3.1-pro-preview and nothing else.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- Is Claude Opus 4.6 better than Gemini 3.1 Pro Preview?
- Better depends on the job; this page compares what the catalog can measure. Gemini 3.1 Pro Preview costs less on both: $1.20 in and $7.20 out per million tokens, against $1.50 in and $7.50 out for Claude Opus 4.6. Claude Opus 4.6 takes 1,000,000 tokens of context against 1,048,576 for Gemini 3.1 Pro Preview. Gemini 3.1 Pro Preview is the newer release. Both run on the same key, so the fair test is your own prompt sent to each model id.