Qwen Models API Cost Calculator & Comparison

Every Qwen model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 45 active models, 45 with public pricing. Prices refreshed daily.

Models tracked

Active

With public pricing

Cheapest input

$0.00/1M

Calculate your Qwen API cost at your workload.

Set your workload — every priced model ranks in real time.

Adjust the workload

Every model below updates in real time.

Conversations per month 50,000

1,00010,00050,000250,0001M10M

Input length

Output length

Repeated questions?

Replies can wait a few hours (batch discount)

Ranked by your monthly bill

No models with public pricing available to compare right now.

Pricing at a glance

Blended $/1M tokens across the lineup.

Blended price uses a 3-to-1 input/output ratio. Green bar = cheapest.

Quick picks

Best Qwen model for your use case.

As of April 2026, Qwen offers 45 active models via API, ranging from $0/1M to $1.04/1M input tokens. The most context-rich model handles up to 1M tokens. Models support vision, deep reasoning, tool use. All prices are USD per 1 million tokens.

Lowest cost

Qwen3 Next 80B A3B Instruct

$0/1M input

Largest context

Qwen3.6 Plus

1M tokens

Deep reasoning

Qwen3 Coder Next

Reasoning mode

Vision / multimodal

Qwen3.5-122B-A10B

Image input

Tool use / agents

Qwen3.5-27B

Function calling

Quality vs price

Qwen benchmarks at a glance.

Each point is one model — X is blended $/1M tokens, Y is the average of available quality benchmarks. Larger bubbles mean larger context windows.

Per-model benchmark scores

Model	Avg	Scores
Qwen3.5 397B A17B	89.2	MMLU88.6MMLU Pro87.8AIME 202591.3
Qwen3.5 Plus 2026-02-15	87.2	MMLU88.6MMLU Pro87.8HumanEval79.3AIME 202591.3IFEval92.6LiveCodeBench83.6
Qwen3.5-27B	86.8	MMLU Pro86.1GPQA Diamond85.5IFEval95LiveCodeBench80.7
Qwen3.5-122B-A10B	83.5	MMLU Pro86.7GPQA Diamond86.6IFEval93.4SWE-Bench Verified72LiveCodeBench78.9
Qwen3 Next 80B A3B Thinking	81.1	MMLU Pro82.7GPQA Diamond77.2AIME 202587.8IFEval88.9LiveCodeBench68.7
Qwen3.5-35B-A3B	81.0	MMLU Pro85.3GPQA Diamond84.2IFEval91.9LiveCodeBench74.6SWE-Bench Verified69.2
Qwen3.5-9B	80.3	MMLU Pro82.5GPQA Diamond81.7IFEval91.5LiveCodeBench65.6
Qwen3 30B A3B Thinking 2507	78.8	MMLU Pro80.9GPQA Diamond73.4AIME 202585IFEval88.9LiveCodeBench66
Qwen3.6 Plus	78.8	SWE-Bench Verified78.8
Qwen2.5 72B Instruct	73.9	MMLU86MMLU Pro58.1HumanEval86.6MATH83.1LiveCodeBench55.5IFEval86.4BBH61.9
Qwen3 Next 80B A3B Instruct	73.6	MMLU Pro80.6AIME 202569.5IFEval87.6LiveCodeBench56.6
Qwen3 Next 80B A3B Instruct	73.6	MMLU Pro80.6AIME 202569.5IFEval87.6LiveCodeBench56.6
Qwen3 Max	73.2	SWE-Bench Verified69.6AIME 202581.6LiveCodeBench69GPQA Diamond72.6
Qwen3 Max Thinking	72.6	GPQA Diamond72.6
Qwen3 Coder 480B A35B	69.6	SWE-Bench Verified69.6
Qwen3 Coder 480B A35B	69.6	SWE-Bench Verified69.6
Qwen3 30B A3B Instruct 2507	67.6	MMLU Pro78.4GPQA Diamond70.4AIME 202561.3IFEval84.7LiveCodeBench43.2
Qwen3 30B A3B	66.8	MMLU81.4MMLU Pro61.5GPQA Diamond43.9AIME 202480.4
Qwen3 32B	64.0	MMLU83.3MMLU Pro65.5AIME 202481.4AIME 202572.9SciPredict17.0
Qwen2.5 Coder 32B Instruct	62.1	HumanEval92.7LiveCodeBench55IFEval72.7BBH52.3MMLU Pro37.9
Qwen3 14B	60.6	MMLU81MMLU Pro61GPQA Diamond39.9
Qwen2.5 7B Instruct	54.9	MMLU74.2HumanEval57.9MATH49.8IFEval75.8BBH34.9MMLU Pro36.5
QwQ 32B	46.4	AIME 202479.5IFEval83.9LiveCodeBench63.4BBH2.9MMLU Pro2.2
Qwen3 235B A22B Instruct 2507	46.1	AIME 202592.3FrontierMath Tier-40.0%
Qwen3 235B A22B Thinking 2507	46.1	AIME 202592.3FrontierMath Tier-40.0%

Open weights

Open Models from Qwen

Qwen ships 32 open-source or open-weights models you can self-host or fine-tune. Each links to its Hugging Face card.

Every model

Every Qwen model — pricing, context & capabilities.

Model	Context	Input /1M	Output /1M	Cached /1M	Batch /1M	Capabilities
Qwen3.6 Plus	1M	$0.325	$1.95	$0.081	$0.163	Deep thinkingImagesTool use
Qwen3 Coder Next	262K	$0.15	$0.8	$0.12	$0.075	Deep thinkingTool use
Qwen3.5-122B-A10B	262K	$0.26	$2.08	$0.065	$0.13	Deep thinkingImagesTool use
Qwen3.5-27B	262K	$0.195	$1.56	$0.025	$0.05	Deep thinkingImagesTool use
Qwen3.5-35B-A3B	262K	$0.163	$1.30	$0.037	$0.075	Deep thinkingImagesTool use
Qwen3.5-9B	262K	$0.1	$0.15	$0.013	$0.025	Deep thinkingImagesTool use
Qwen3.5-Flash	1M	$0.065	$0.26	$0.025	$0.05	Deep thinkingImagesTool use
Qwen3.5 397B A17B	262K	$0.39	$2.34	$0.195	$0.3	Deep thinkingImagesTool use
Qwen3.5 Plus 2026-02-15	1M	$0.26	$1.56	$0.1	$0.2	Deep thinkingImagesTool use
Qwen-Plus	1M	$0.26	$0.78	$0.052	$0.2	Deep thinkingImagesTool use
Qwen3 VL 30B A3B Instruct	131K	$0.13	$0.52	$0.02	$0.04	ImagesTool use
Qwen3 VL 30B A3B Thinking	131K	$0.13	$1.56	$0.02	$0.04	Deep thinkingImagesTool use
Qwen3 VL 32B Instruct	131K	$0.104	$0.416	$0.037	$0.075	ImagesTool use
Qwen3 VL 8B Instruct	131K	$0.08	$0.5	$0.01	$0.02	ImagesTool use
Qwen3 VL 8B Thinking	131K	$0.117	$1.36	$0.01	$0.02	Deep thinkingImagesTool use
Qwen3 VL 235B A22B Instruct	262K	$0.2	$0.88	$0.11	$0.1	ImagesTool use
Qwen3 VL 235B A22B Thinking	131K	$0.26	$2.60	$0.065	$0.13	Deep thinkingImagesTool use
Qwen3 Max	262K	$0.78	$3.90	$0.156	$0.6	Tool use
Qwen3 Max Thinking	262K	$0.78	$3.90	$0.3	$0.6	Deep thinkingTool use
Qwen3 Next 80B A3B Instruct	262K	$0.09	$1.10	$0.025	$0.05	Tool use
Qwen3 Next 80B A3B Instruct	262K	$0.0	$0.0	$0.0	$0.0	Tool use
Qwen3 Next 80B A3B Thinking	131K	$0.098	$0.78	$0.025	$0.05	Deep thinkingTool use
Qwen3 Coder Flash	1M	$0.195	$0.975	$0.039	$0.098	Tool use
Qwen3 Coder 30B A3B Instruct	160K	$0.07	$0.27	$0.013	$0.025	Tool use
Qwen Plus 0728 (thinking)	1M	$0.26	$0.78	$0.1	$0.2	Deep thinkingImagesTool use
Qwen3 235B A22B Instruct 2507	262K	$0.071	$0.1	$0.018	$0.035	Tool use
Qwen3 235B A22B Thinking 2507	262K	$0.13	$0.6	$0.018	$0.035	Deep thinkingTool use
Qwen3 30B A3B Instruct 2507	262K	$0.09	$0.3	$0.013	$0.025	Tool use
Qwen3 30B A3B Thinking 2507	131K	$0.08	$0.4	$0.08	$0.025	Deep thinkingTool use
Qwen3 Coder 480B A35B	262K	$0.22	$1.00	$0.022	$0.11	Tool use
Qwen3 Coder 480B A35B	262K	$0.0	$0.0	$0.0	$0.0	Tool use
Qwen3 Coder Plus	1M	$0.65	$3.25	$0.13	$0.5	Tool use
Qwen-Turbo	131K	$0.033	$0.13	$0.006	$0.025	Deep thinkingTool use
Qwen3 14B	41K	$0.06	$0.24	$0.018	$0.035	Deep thinkingTool use
Qwen3 30B A3B	41K	$0.08	$0.28	$0.025	$0.05	Deep thinkingTool use
Qwen3 32B	41K	$0.08	$0.24	$0.04	$0.05	Deep thinkingTool use
Qwen3 8B	41K	$0.05	$0.4	$0.05	$0.02	Deep thinkingTool use
QwQ 32B	131K	$0.15	$0.58	$0.015	$0.075	Deep thinkingTool use
Qwen2.5 VL 72B Instruct	32K	$0.25	$0.75	$0.063	$0.125	ImagesTool use
Qwen-Max	33K	$1.04	$4.16	$0.208	$0.8	ImagesTool use
Qwen2.5 Coder 32B Instruct	33K	$0.66	$1.00	$0.022	$0.045	Tool use
Qwen2.5 7B Instruct	33K	$0.04	$0.1	$0.01	$0.02	Tool use
Qwen2.5 72B Instruct	33K	$0.12	$0.39	$0.03	$0.06	Tool use
Qwen VL Max	131K	$0.52	$2.08	$0.4	$0.26	ImagesTool use
Qwen VL Plus	131K	$0.137	$0.409	$0.027	$0.105	ImagesTool use

FAQ

よくある質問

Pricing patterns, best-known use cases, and how this provider stacks up.

Get instant answers from our AI agent

Qwen API pricing ranges from $0 to $1.04 per 1M input tokens. Output tokens cost more than input on every model. Prices are per 1 million tokens (1M ≈ 750,000 words). Use the calculator above to estimate your monthly spend at your actual workload.

Qwen3 Next 80B A3B Instruct is the lowest-priced Qwen model with public pricing at $0/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.

Qwen-Max is Qwen's highest-tier model at $1.04/1M input. It delivers the most sophisticated reasoning, instruction-following, and nuance. For workloads that don't require frontier performance, a mid-tier model typically cuts inference costs substantially.

Qwen3.6 Plus, Qwen3 Coder Next, Qwen3.5-122B-A10B and 21 more support deep reasoning mode, which improves performance on multi-step coding, debugging, and code review. For simpler autocomplete or snippet generation, a faster, cheaper model often delivers acceptable quality at a fraction of the cost.

Qwen3.6 Plus, Qwen3 Coder Next, Qwen3.5-122B-A10B and 42 more support function calling (tool use), required for agentic workflows. Agents need a model that reliably follows structured output schemas — test with your specific tool definitions before committing to production volumes.

Yes — Qwen3.6 Plus, Qwen3.5-122B-A10B, Qwen3.5-27B, Qwen3.5-35B-A3B and 17 more accept image input alongside text. You can pass screenshots, photos, charts, and documents for analysis. Vision adds no separate line-item on most Qwen models — you're billed for the token equivalent of the image.

Yes — Qwen supports prompt caching (discounts for repeated context) and batch processing (accept a delay, cut costs ~50%). These rates appear in the table above under "Cached /1M" and "Batch /1M." Caching pays off quickly if your prompts share a long system prompt or document prefix across many calls.

Qwen has historically adjusted prices when launching new model generations, often cutting rates to stay competitive. Buzzi.ai snapshots pricing daily — you can subscribe to price-drop alerts on any Qwen model using the "Alert me" button on its detail page.

Use the main comparison wizard to run the same calculator across Qwen, Anthropic, Google, Meta, Mistral, and 20+ other providers. Set your exact workload and get a ranked cost chart in under a minute.

Qwen3.6 Plus, Qwen3 Coder Next, Qwen3.5-122B-A10B, Qwen3.5-27B and 20 more offer an extended thinking or reasoning mode. The model spends extra compute "thinking" before answering — slower and more expensive, but meaningfully better on complex, multi-step problems. Standard mode is faster and cheaper for routine tasks.

Look wider

Compare Qwen against other providers.

Open the full wizard — pick a use case, set your usage, and cross-compare against OpenAI, Anthropic, Google, and 20+ more.

Open the comparison wizard

About

Insights

Streamline

Integration

Solutions

Healthcare AI

Use Cases

Industries