Models

Claude Sonnet 4.6 Thinking vs Qwen3.8 Max Preview

Output tokens cost $15.00 per million on Claude Sonnet 4.6 Thinking and $1.01 per million on Qwen3.8 Max Preview. Input tokens cost $3.00 per million on Claude Sonnet 4.6 Thinking and $0.34 per million on Qwen3.8 Max Preview. Cached input tokens are billed at $0.30 per million on Claude Sonnet 4.6 Thinking and $0.03 per million on Qwen3.8 Max Preview. Context lengths are 200,000 tokens on Claude Sonnet 4.6 Thinking and 983,616 tokens on Qwen3.8 Max Preview. Time to first token (TTFT) measured on AIHubMix is 1.2s on Claude Sonnet 4.6 Thinking and 2.4s on Qwen3.8 Max Preview. Measured output throughput is 67.8 tok/s on Claude Sonnet 4.6 Thinking and 48.1 tok/s on Qwen3.8 Max Preview. On the LMArena coding leaderboard Claude Sonnet 4.6 Thinking scores 1528 and Qwen3.8 Max Preview scores 1520.

AnthropicClaude Sonnet 4.6 ThinkingQwenQwen3.8 Max Preview
Anthropic logo
Claude Sonnet 4.6 Thinking
Anthropic · image, text → text

Claude sonnet 4.6 does not enable reasoning mode by default. To access its deep reasoning capabilities, users would typically need to call the native Claude API. To make this capability available through an OpenAI-compatible interface, we provide the claude-sonnet-4-6-think model, which has reasoning mode pre-enabled and a default 32k-token context window, allowing it to be called directly via the OpenAI unified API. Claude sonnet 4.5 Think is a reasoning-focused variant of Claude sonnet 4.6 designed for advanced tasks that require rigorous reasoning, complex decision-making, and long-chain analysis. Aside from its enhanced reasoning mechanism, all other capabilities remain consistent with the standard Claude sonnet 4.6 model, making it well suited for complex engineering problem decomposition, multi-stage planning, and logic-intensive analysis.

Input$3.00 /M
Output$15.00 /M
Qwen logo
Qwen3.8 Max Preview
Qwen · text, image → text

Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows. Launch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.

Input$0.34 /M
Output$1.01 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Claude Sonnet 4.6 Thinking
Qwen3.8 Max Preview
Input /M
$3.00
$0.34
Output /M
$15.00
$1.01
Cache read /M
$0.30
$0.03
Context length
200,000
983,616
Max output
32,000
131,072
Time to First Token
1.2 s
2.4 s
Throughput
67.8 tok/s
48.1 tok/s
Modalities
imagetext
textimage
Supported Parameters
thinkingtoolsfunction callingstructured outputs
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
-
-

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

claude-sonnet-4-6-thinkqwen3.8-max-preview

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

claude-sonnet-4-6-thinkqwen3.8-max-preview

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
claude-sonnet-4-6-thinkqwen3.8-max-preview
14201460150015401580
Overall
14721481
Coding
15201528
Math
14631504
Hard prompts
15031506
Instruction following
14761478
Multi-turn
14811496
Creative writing
14501469
Longer query
14931497
Chinese
15101545
English
14841486
Vision
claude-sonnet-4-6-thinkqwen3.8-max-preview
1240128013201360
Overall
12751302
OCR
12901317
Diagram
13061331
Homework
13021335
WebDev Arena
claude-sonnet-4-6-thinkqwen3.8-max-preview
1480156016401720
Overall
15221669
React
15121678
HTML
15291628
Gaming
15421733
Simulations
15221665
Data analytics
15191614

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

Qwen3.8 Max Preview
$35.49 /mo
Claude Sonnet 4.6 Thinking
$405 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: Claude Sonnet 4.6 Thinking, Qwen3.8 Max Preview?

Qwen3.8 Max Preview: $1.01/M output tokens; Claude Sonnet 4.6 Thinking: $15.00/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Claude Sonnet 4.6 Thinking: 1528; Qwen3.8 Max Preview: 1520 (LMArena coding leaderboard).

Which responds faster?

Claude Sonnet 4.6 Thinking: 1.2s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

Claude Sonnet 4.6 Thinking accepts 200,000 and Qwen3.8 Max Preview accepts 983,616 input tokens. Maximum output per request is 32,000 tokens on Claude Sonnet 4.6 Thinking and 131,072 tokens on Qwen3.8 Max Preview.

Which one generates tokens faster?

Claude Sonnet 4.6 Thinking at 67.8 tok/s and Qwen3.8 Max Preview at 48.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Claude Sonnet 4.6 Thinking accepts image and text input and supports thinking, tool calling, function calling and structured outputs; Qwen3.8 Max Preview accepts text and image input and supports tool calling, function calling, structured outputs, web search, long context and thinking.

Can I call Claude Sonnet 4.6 Thinking and Qwen3.8 Max Preview with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.