Gemini 3.6 Flash vs Qwen3.7 Plus
Which one, when — curated verdict, not a benchmark table
Pick gemini-3.6-flash when audio is part of the input: it accepts text, image, video and audio (audio input at $5 per million tokens, audio cache reads at $0.5), with a 1048576-token context window. Choose qwen3.7-plus for text, image and video work at lower cost — $0.4 input and $1.6 output versus $1.5 and $7.5, roughly 3.75x and 4.7x cheaper, on a 1000000-token context with the same 65536 max output. Qwen3.7 Plus also lets you turn thinking off and flags reasoning and long-context, while Gemini 3.6 Flash always thinks.
Pricing
| Gemini 3.6 Flash | Qwen3.7 Plus | Δ | |
|---|---|---|---|
| Input / 1M tokens | $1.5 | $0.4 | 3.8× |
| Output / 1M tokens | $7.5 | $1.6 | 4.7× |
| Cache read / 1M tokens | $0.15 | $0.08 | 1.9× |
| Cache write | — | 1.25x | — |
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
| Gemini 3.6 Flash | Qwen3.7 Plus | |
|---|---|---|
| Tool use | yes | yes |
| Thinking control | always on | configurable |
| Structured output | yes | yes |
| Prompt caching | implicit + explicit | implicit + explicit |
| Cache lifetime | not published | explicit: 5m, reset on hit |
| Minimum cached prefix | 4096 tokens | 1024 tokens |
Specs
| Gemini 3.6 Flash | Qwen3.7 Plus | |
|---|---|---|
| Input modalities | text image audio video | text image video |
| Output modalities | text | text |
| Released | — | 2026-06-01 |
| Knowledge cutoff | 2026-03 | — |
| Context window | 1M | 1M |
| Max output | 66K | 66K |
| Thinking parameter | thinkingLevel |
|
| Accepted values |
| enable_thinking
thinking_budget
preserve_thinking
|
| Default | medium | on the Qwen3.7 Plus series is hybrid thinking with thinking enabled by default, and preserve_thinking is off |
Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Gemini 3.6 Flash · Qwen3.7 Plus
One prompt, both models — measured through the gateway
Gemini 3.6 Flash passed · 3 sentences
Enabling reasoning causes the model to generate thousands of internal "thinking" tokens behind the scenes to process logic before delivering the final response. Because our vendor bills us for every token generated—including these intermediate processing steps—our billable output volume per query surged significantly. Since output tokens carry a much higher unit cost than input tokens, this jump in processing volume directly doubled our overall spend.
out 893 tok (+816 thinking) latency 4.7 s
Qwen3.7 Plus passed · 3 sentences
Enabling reasoning requires the model to generate extensive internal "thinking" tokens to process complex logic before delivering a final answer. Because our vendor charges us per token consumed, this hidden computational overhead effectively doubles our output volume for the exact same number of user requests. Consequently, our costs have doubled because we are now paying for the model's increased processing time to achieve higher-quality, more accurate results.
out 1428 tok (+1345 thinking) latency 25.2 s
Instruction following (exactly three sentences — countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.
Gemini 3.6 Flash passed · 8/8 cases
Here is the fixed function along with an explanation of the bugs: ```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 best = max(best, cur) return best ``` ### Explanation The original function initialized `cur` and `best` to `0` and incremented `cur` on matching adjacent items, which meant it was counting identical adjacent *pairs* rather than the total number of *elements* in a run. This caused single-element inputs to skip the loop and return `0` instead of `1`, and undercounted all run lengths by 1 (for example, a run of two items at the end of the list resulted in `cur = 1`). […]
out 2034 tok (+1768 thinking) latency 10.0 s
Qwen3.7 Plus passed · 8/8 cases
## Fixed Code ```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 best = max(best, cur) return best ``` ## Bug Explanation The function has two related bugs rooted in how it counts run lengths. First, `cur` is initialized to `0` and only incremented on matches, so it counts the number of *transitions* between equal elements rather than the total elements in the run—a run of N identical items only reaches `cur = N − 1`, undercounting by one. This also causes the single-element case to return `0`, since the loop never executes and `cur` never increments. […]
out 2317 tok (+2005 thinking) latency 40.5 s
Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.
Gemini 3.6 Flash passed · 5/5 fields, guidance "withheld"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": null, "guidance": "withheld" } ```
out 2843 tok (+2783 thinking) latency 13.1 s
Qwen3.7 Plus passed · 5/5 fields, guidance null
{ "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }
out 1807 tok (+1750 thinking) latency 31.6 s
Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.
Gemini 3.6 Flash missed · 60 words, 0 banned, 0 questions
72: reducing 73: your 74: monthly 75: token 76: spend. S6 (21): 77: You 78: can 79: easily 80: set 81: custom 82: expiration 83: rules, 84: configure 85: TTL 86: settings, 87: and 88: manage 89: cache 90: invalidation 91: across 92: all 93: vendors 94: from 95: one 96: centralized 97: dashboard. S7 (23): 98: Start 99: optimizing […]
out 4092 tok (+3929 thinking) latency 16.3 s
Qwen3.7 Plus passed · 120 words, 0 banned, 1 question
Introducing PromptCache, our new API gateway feature designed to store and reuse prompts across multiple artificial intelligence providers. Have you ever noticed how repeatedly sending identical queries drains your budget and increases latency? PromptCache solves this by intelligently storing responses at the gateway level. When your application requests the same prompt from a different provider, the system instantly returns the cached result. This drastically reduces API costs and accelerates response times for your users. You can configure custom expiration times and set specific fallback rules for each vendor. You must stop paying twice for the exact same computation. Please upgrade your entire infrastructure today and experience much faster and cheaper integrations without changing a single line of your application code.
out 4453 tok (+4312 thinking) latency 76.8 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="gemini-3.6-flash",
# model="qwen3.7-plus", # uncomment this line, comment the one above
messages=[{"role": "user", "content": "Summarize this diff"}],
)
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: "gemini-3.6-flash",
// model: "qwen3.7-plus", // uncomment this line, comment the one above
messages: [{ role: "user", content: "Summarize this diff" }],
});
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": "gemini-3.6-flash",
# "model": "qwen3.7-plus", # uncomment this line, comment the one above
"messages": [{"role": "user", "content": "Hello"}]
}'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: "gemini-3.6-flash",
// Model: "qwen3.7-plus", // uncomment this line, comment the one above
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gemini-3.6-flash")
// .model("qwen3.7-plus") // uncomment this line, comment the one above
.addUserMessage("Summarize this diff")
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));FAQ
Which is cheaper, Gemini 3.6 Flash or Qwen3.7 Plus?
Qwen3.7 Plus is cheaper on input / 1m tokens ($0.4 vs $1.5, 3.8× 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 Gemini 3.6 Flash against Qwen3.7 Plus 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 Gemini 3.6 Flash and Qwen3.7 Plus 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.