MiniMax M3 vs Qwen3.8 Max

MiniMax M3 has been retired from our catalogue. Its figures below are the last published rates; calls to it are no longer served, while the other model in this comparison is.

vs

Which one, when

minimax-m3 is the cheaper of the two on every line of the rate card, at $0.3 input and $1.2 output versus $2 and $6 for qwen3.8-max - roughly 6.7x and 5x less - and it also accepts video alongside text and image, carries a 1000000-token context with up to 524288 tokens of output, and lets you turn thinking off. qwen3.8-max costs more and caps output at 131072 tokens on a 983616-token context, so reach for it when you want Alibaba's newer August 2026 model with an explicit vision flag on text and image work. For high-volume, long-output or video-input jobs, minimax-m3 is the economical pick.

Benchmarks

MiniMax M3: the vendor has not published benchmark scores.

Above averageNo peer higherQwen3.8 Max31 / 408 / 40
MiniMax M3 Qwen3.8 Max other models measured peer average ★ no peer scored higher
SWE-Bench Pro
N/A
67.7%
AndroidBench
N/A
75.1%
Cybergym
N/A
78.5%
HealthBench
N/A
no peer scored higher 60.2%
JobBench
N/A
53.4%
PLawBench
N/A
no peer scored higher 73.2%
GPQA Diamond
N/A
92.6%
Agents' Last Exam
N/A
27%

Vendor-published: Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Alibaba (Qwen) Anthropic Anthropic Anthropic Anthropic ByteDance DeepSeek DeepSeek Google Google Google Google MiniMax Moonshot Moonshot OpenAI OpenAI OpenAI OpenAI OpenAI OpenAI OpenAI Tencent Z.ai Z.ai Z.ai Z.ai

Pricing

MiniMax M3 Qwen3.8 Max Δ
Input / 1M tokens $0.3 $2 0.15×
Output / 1M tokens $1.2 $6 0.2×
Cache read / 1M tokens $0.06 $0.25 0.24×
Cache write no separate charge 1.25x -

Rates from the live catalogue at build time; each model page carries the current rate card.

Where they sit · input price per 1M tokens across all 91 chat models on this billing unit (log scale)

MiniMax M3 · $0.3 Qwen3.8 Max · $2
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

Capabilities

MiniMax M3 Qwen3.8 Max
Tool calling yes yes
Thinking control configurable yes (vendor dial not published)
Structured output - yes
Prompt caching implicit (automatic) implicit + explicit
Cache lifetime not published explicit: 5m, reset on hit
Minimum cached prefix 512 tokens 1,024 tokens

Specs

MiniMax M3 Qwen3.8 Max
Input modalities text image video text image
Output modalities text text
Released 2026-06-01 2026-08-03
Context window 1,000,000 983,616
Max output 524,288 131,072
Thinking parameter
  • thinking.type
  • reasoning_split
-
Accepted values
thinking.type
  • adaptive
  • disabled
reasoning_split
  • boolean
-
Default adaptive: thinking on, with the model deciding when extra reasoning helps -

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: MiniMax M3 · Qwen3.8 Max

One prompt, both models, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

MiniMax M3 passed · 3 sentences

Reasoning models don't just answer — they first generate extensive internal "thinking" tokens to work through the problem step-by-step, and you're billed for all of those tokens even though users never see them. A query that previously cost ~200 tokens may now cost 2,000–10,000 once reasoning is enabled, multiplying per-query spend by roughly 5–50x while the visible output stayed the same size — that's the doubling. The lever is tuning: cap reasoning effort on simple queries, cache the reasoning traces, and reserve the full reasoning model for only your hardest 10–20% of requests, which typically restores 60–80% of the savings.

out 764 tok (+629 thinking) latency 3.5 s

Qwen3.8 Max passed · 3 sentences

Enabling reasoning makes the model produce additional hidden steps before responding, and those tokens are billable. It also tends to lengthen each interaction because the model works through more possibilities before settling on an answer. Therefore, the bill doubled mainly due to higher compute and token usage per request, not necessarily because the number of requests doubled.

out 378 tok (+305 thinking) latency 8.6 s

Instruction following (exactly three sentences, so countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

MiniMax M3 passed · 8/8 cases

The bug is that the loop starts at index 1 and treats `cur` as the number of *equal transitions* rather than the run length, so a run of *k* consecutive equal items is reported as `k − 1`, and a single-element list (where the loop body never executes) returns 0 instead of 1. A correct version tracks the actual run length by seeding `cur = 1` and resetting it to 1 (not 0) on a mismatch: ```python def longest_run(xs): if not xs: return 0 best = 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 ``` Now `[5]` returns `1`, `[1,1,1]` returns `3`, and a run like `[1,2,2,2]` that ends at the last index is correctly captured as `3` because `cur` is updated before `best` is compared on every iteration, including the final one.

out 845 tok (+596 thinking) latency 3.5 s

Qwen3.8 Max passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 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 ``` The bug is that the original code starts `best` and `cur` at `0`, so it counts adjacent equal *transitions* rather than the number of items in the run. A run of length `n` has only `n - 1` equal-neighbor transitions, so single-element inputs return `0`, and runs that reach the end are undercounted by one. Initializing the current run to `1` for the first element, resetting it to `1` on a break, and updating `best` from that count fixes the off-by-one.

out 1616 tok (+1411 thinking) latency 34.7 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

MiniMax M3 passed · 5/5 fields, guidance null

```json { "company": null, "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": null, "guidance": null } ```

out 1002 tok (+955 thinking) latency 3.6 s

Qwen3.8 Max passed · 5/5 fields, guidance null

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null }

out 1199 tok (+1141 thinking) latency 24.4 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

MiniMax M3 passed · 121 words, 0 banned, 1 question

Introducing PromptCache, our intelligent caching layer for the API gateway. Tired of paying twice for identical requests? The feature stores prompt-response pairs across every connected provider, returning cached results instead of hitting costly endpoints. Deployment requires only a single configuration flag, and semantic similarity detection happens automatically. Latency drops up to 70% on repeated traffic while costs follow the same downward curve. Developers access detailed cache hit metrics, eviction logs, and provider breakdowns through the dashboard. Whether routing to OpenAI, Anthropic, or local models, every cached token saves time and money. The cache respects TTL policies, supports manual purging, and encrypts stored content. Available today for Pro and Enterprise tiers—enable PromptCache on existing endpoints and watch inference bills shrink immediately.

out 2808 tok (+2656 thinking) latency 6.0 s

Qwen3.8 Max passed · 120 words, 0 banned, 1 question

Today, our API gateway adds prompt caching across major model providers. It stores prompts and responses in one fast cache layer. Teams can lower token spend, reduce latency, and repeat reliable answers. The feature supports OpenAI, Anthropic, Google, and Mistral through one configuration. You can set retention rules, scope access, and invalidate entries quickly. How does your team maintain consistent results during provider outages? Approved cached responses keep applications stable while fallback routes recover. The dashboard shows hit rates, savings, latency, and provider usage. Engineers receive audit trails for every cached prompt, enabling safer testing. Product managers can compare cost trends before and after cache adoption. Start with a small route, then safely expand caching to production traffic right now.

out 2744 tok (+2591 thinking) latency 46.3 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="minimax-m3",
    # model="qwen3.8-max",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

Which is cheaper, MiniMax M3 or Qwen3.8 Max?

MiniMax M3 is cheaper on the "Input / 1M tokens" row ($0.3 vs $2, 6.7× apart). Other rows may point the other way; the table above carries the full rate card, and real cost depends on your mix.

Can I A/B test MiniMax M3 against Qwen3.8 Max without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key. Switching is a one-line change to the model id, so you can route a fraction of traffic to each and compare bills directly.

Do MiniMax M3 and Qwen3.8 Max support prompt caching?

Yes. Both bill cache 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.

Related comparisons

From our measured studies