Claude Opus 5 vs Gemini 3.1 Pro
Which one, when — curated verdict, not a benchmark table
Pick Gemini 3.1 Pro when the workload is long-document and multimodal: it reads text, image, audio and video at $2/$12 against Opus 5’s $5/$25. Pick Claude Opus 5 for deep agentic coding and long-horizon tool use, and note its tokenizer bills identical text as more tokens than the Sonnet 4.6 generation — compare token counts, not sticker prices.
Pricing
| Claude Opus 5 | Gemini 3.1 Pro | Δ | |
|---|---|---|---|
| Input / 1M tokens | $5 | $2 | 2.5× |
| Output / 1M tokens | $25 | $12 | 2.1× |
| Cache read / 1M tokens | $0.5 | $0.2 | 2.5× |
| Cache write | 1.25x (5m) / 2x (1h) | — | — |
Rates from the live catalog at build time; each model page carries the current card.
Where they sit — input price per 1M tokens across all 63 chat models on this billing unit (log scale)
Capabilities
| Claude Opus 5 | Gemini 3.1 Pro | |
|---|---|---|
| Tool use | yes | yes |
| Thinking control | configurable | always on |
| Structured output | yes | yes |
| Prompt caching | explicit (you mark the prefix) | implicit + explicit |
| Cache lifetime | 5m default, 1h option | not published |
| Minimum cached prefix | 1024 tokens | 4096 tokens |
Specs
| Claude Opus 5 | Gemini 3.1 Pro | |
|---|---|---|
| Input modalities | text image | text image audio video |
| Output modalities | text | text |
| Released | 2026-07-24 | 2026-02-19 |
| Knowledge cutoff | 2026-05 | 2025-01 |
| Context window | 1M | 1M |
| Max output | 128K | 66K |
| Thinking parameter |
| thinkingLevel |
| Accepted values | thinking.type
effort
|
|
| Default | thinking on effort
| high |
Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Claude Opus 5 · Gemini 3.1 Pro
One prompt, both models — measured through the gateway
Claude Opus 5 passed · 3 sentences
When reasoning is enabled, the model generates a hidden chain of "thinking" tokens before it writes the visible answer, and those internal tokens are billed at the output rate even though no one ever sees them — commonly 3–10x more tokens than the response itself. Because output tokens are priced several times higher than input tokens, that added volume hits us at our most expensive rate, which is why the bill roughly doubled while our request count stayed flat. The spend is controllable: we can cap the reasoning budget per call, route only genuinely hard requests to reasoning mode and cheaper models for the rest, and track cost per successfully completed task rather than cost per token, since a single correct answer usually beats three cheap retries plus human cleanup.
out 529 tok latency 9.0 s
Gemini 3.1 Pro passed · 3 sentences
Enabling the AI's reasoning capability forces the model to generate a massive amount of invisible "thought" tokens to logically work through complex problems before delivering its final answer. Because our vendor's pricing model charges us for total computational effort—including all of these hidden background tokens—our billable usage effectively doubled per request. While this directly increases our upfront software expenses, we are trading this higher compute cost for a drastic reduction in expensive downstream errors and manual human rework.
out 1412 tok (+1318 thinking) latency 12.7 s
Instruction following (exactly three sentences — countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.
Claude Opus 5 passed · 8/8 cases
## Fixed version ```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 if cur > best: best = cur return best ``` ## The bug The counters were tracking the wrong quantity: `cur` counted *matching adjacent pairs* rather than *elements in the current run*, and both counters started at `0` instead of `1`. Since a run of length *n* contains only *n − 1* adjacent equal pairs, every result came back one too small — `[1, 1]` returned 1, `[3, 3, 3]` returned 2 — and a single-element list returned 0 because the loop body never executed and `best` kept its initial value of `0`. […]
out 1094 tok latency 16.1 s
Gemini 3.1 Pro passed · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The original function initializes `cur` and `best` to 0 and only increments `cur` when two adjacent elements are equal. This effectively counts the number of *matching consecutive pairs* (or transitions) rather than the actual number of *elements* in the run, causing all calculated lengths to be […]
out 4092 tok (+3933 thinking) latency 31.1 s
Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.
Claude Opus 5 passed · 5/5 fields, guidance "Withheld pending Q4 close"
```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` Notes on judgment calls: - **quarter**: "September quarter" is labeled Q3 because the text refers to an upcoming "Q4 close," implying a calendar-aligned fiscal year. No fiscal year is given. - **revenue_usd_m**: 412 is stated as constant-currency and hedged ("call it"), so it's approximate; the currency is not explicitly stated as USD. - **growth_pct**: "up eleven and change" means slightly more than 11, so 11 is a floor rather than an exact figure.
out 539 tok latency 7.6 s
Gemini 3.1 Pro passed · 5/5 fields, guidance "withheld"
```json { "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": "11 and change", "guidance": "withheld" } ```
out 1806 tok (+1743 thinking) latency 14.1 s
Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.
Claude Opus 5 passed · 123 words, 0 banned, 1 question
**Cross-Provider Prompt Caching** We're introducing Cross-Provider Prompt Caching in the API Gateway. Repeated system prompts, long documents, and few-shot examples are stored once at the gateway layer and reused across OpenAI, Anthropic, Google, and self-hosted models. Instead of paying full input token costs on every request, your application sends a cache reference, and the gateway rehydrates the context before forwarding it downstream. Why does that matter? Teams running high-volume agents and retrieval pipelines typically see input token spend fall 40 to 70 percent, with median latency dropping by several hundred milliseconds. Caches are scoped per project, encrypted at rest, and invalidated automatically when a prompt template changes. Enable it with a single header, and see the docs for TTL tuning and per-route controls.
out 1593 tok latency 19.1 s
Gemini 3.1 Pro passed · 120 words, 0 banned, 1 question
We are excited to announce universal prompt caching for our API gateway. Handling multiple AI models usually means paying for redundant prompts across various platforms. Why should you pay twice for identical queries? Now, our gateway automatically stores and retrieves exact prompt matches regardless of the backend provider you select. This reduces latency and significantly cuts your inference costs. Whether you route a request to one service today or a different vendor tomorrow, our intelligent caching layer intercepts the call and serves the saved response instantly. Developers can configure cache expiration times and specify matching criteria directly in the control panel. Experience faster response times and optimized resource usage starting today. Upgrade your software client to version two right now.
out 4060 tok (+3929 thinking) latency 28.6 s
Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.
Switch between them with one line
Both ids are in every tab below — the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="claude-opus-5",
# model="gemini-3.1-pro-preview", # uncomment this line, comment the one above
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "claude-opus-5",
// model: "gemini-3.1-pro-preview", // uncomment this line, comment the one above
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5",
# "model": "gemini-3.1-pro-preview", # uncomment this line, comment the one above
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "claude-opus-5",
// Model: "gemini-3.1-pro-preview", // uncomment this line, comment the one above
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("claude-opus-5")
// .model("gemini-3.1-pro-preview") // uncomment this line, comment the one above
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));FAQ
Which is cheaper, Claude Opus 5 or Gemini 3.1 Pro?
Gemini 3.1 Pro is cheaper on input / 1m tokens ($2 vs $5, 2.5× apart). Other rows may point the other way — the table above carries the full card, and real cost depends on your mix.
Can I A/B test Claude Opus 5 against Gemini 3.1 Pro without two integrations?
Yes. Both are served through the same OpenAI-compatible endpoint with one API key — switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.
Do Claude Opus 5 and Gemini 3.1 Pro support prompt caching?
Yes — both bill cached reads below their input rate, so warm-prefix workloads cost less than the list rates suggest. The exact cache-read rows are in the pricing table above.