qwen3-thinking
Developer: Alibaba
Alibaba Qwen3 Thinking is a reasoning-oriented model in the Qwen3 series, designed for multi-step problem solving and deliberate chain-of-thought tasks.
Also known as
Qwen3 Thinking by Alibaba is available through 56 API providers on LMSpeed. Compare API pricing from $0.0010 to $75.00 per million input tokens across providers. In speed benchmarks, the fastest provider reaches 53 tok/s.
Compare Qwen3 Thinking API pricing across 56 providers. Input prices range from $0.0010 to $75.00 per million input. 10dian-API offers the lowest rate at $0.0010/M.
| Provider | Model Variant | Audit | Input ($/M) | Output ($/M) | Speed (t/s) | First token |
|---|---|---|---|---|---|---|
V-API100% | qwen3-30b-a3b-thinking-2507 | — | $0.750 | $7.50 | — | — |
| qwen3-235b-a22b-thinking-2507 | — | $2.00 | $20.00 | — | — | |
柏拉图AI100% | qwen3-30b-a3b-thinking-2507 | — | $0.104 | $1.03 | — | — |
| qwen3-235b-a22b-thinking-2507 | — | $0.274 | $2.74 | — | — | |
天絮 API100% | Qwen/Qwen3-30B-A3B-Thinking-2507 | — | $0.013 | $0.043 | — | — |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $0.043 | $0.429 | — | — | |
| Qwen3-235B-A22B-Thinking | — | $10.71 | $10.71 | — | — | |
| qwen3-235b-a22b-think | — | $10.71 | $10.71 | — | — | |
Seamee API100% | Qwen/Qwen3-30B-A3B-Thinking-2507 | — | $0.090 | $0.300 | — | — |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $0.100 | $0.100 | — | — | |
AAAI100% | qwen3-30b-a3b-thinking-2507 | — | $0.750 | $7.50 | — | — |
| qwen3-235b-a22b-thinking-2507 | — | $2.00 | $20.00 | — | — | |
钱多多 API100% | Qwen/Qwen3-30B-A3B-Thinking-2507 | — | $0.367 | $3.67 | — | — |
| qwen3-30b-a3b-thinking-2507 | — | $0.367 | $3.67 | — | — | |
| qwen/qwen3-235b-a22b-thinking-2507 | — | $0.979 | $9.79 | — | — | |
| qwen3-235b-a22b-thinking-2507 | — | $0.979 | $9.79 | — | — | |
| Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $36.71 | $36.71 | — | — | |
毫秒API100% | qwen3-30b-a3b-thinking-2507 | — | $0.760 | $7.50 | — | — |
| qwen3-235b-a22b-thinking-2507 | — | $2.00 | $20.00 | — | — | |
Newagiai100% | qwen3-30b-a3b-thinking-2507 | — | $0.104 | $1.03 | — | — |
Pricing data from provider public APIs
Compare speed and latency performance across all API providers.
| Provider | Speed | Latency | Tests |
|---|---|---|---|
阿里云百炼 DashScope qwen3-235b-a22b-thinking-2507 | 53.49 tok/s | 13.88s | 20 |
Qwen3-235B-A22B-Thinking-2507 | 48.00 tok/s | 13.71s | 5 |
qwen3-235b-a22b-thinking-2507 | 18.92 tok/s | 29.02s | 10 |
Showing 1-3 of 3 providers
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
deepseek-v3-2
DeepSeek V3.2 is a large language model in the DeepSeek V3 series, offering advanced reasoning, code generation, and multimodal capabilities.
deepseek-v3
DeepSeek V3 is a large language model in the DeepSeek series, offering advanced reasoning and general-purpose text generation capabilities.
deepseek-r1
DeepSeek R1 is a reasoning-focused language model in the DeepSeek series, designed for complex reasoning, problem-solving, and analytical tasks.
claude-opus-4-6
Anthropic Claude Opus 4.6 is a large language model in the Claude series, offering advanced reasoning, code generation, and multimodal capabilities.
gemini-2-5-pro
Google Gemini 2.5 Pro is a large language model in the Gemini series, offering advanced reasoning, code generation, and multimodal capabilities.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
