Qwen API Pricing
Compare input and output token prices across AI language models.
| Provider | Model | Input per 1M tokens | Output per 1M tokens | |
|---|---|---|---|---|
Qwen | Qwen3.7-Flash | $0.03 | $0.13 | View |
Qwen | Qwen3-30B-A3B FP8Open weights | $0.05 | $0.34 | View |
Qwen | Qwen3.5-35B-A3BOpen weights | $0.06 | $0.46 | View |
Qwen | Qwen3.6-35B-A3BOpen weights | $0.07 | $0.42 | View |
Qwen | Qwen3.5-Flash | $0.09 | $0.37 | View |
Qwen | Qwen3.8-Flash | $0.09 | $0.37 | View |
Qwen | Qwen3.5-27BOpen weights | $0.09 | $0.69 | View |
Qwen | Qwen3.5-122B-A10BOpen weights | $0.12 | $0.92 | View |
Qwen | Qwen3.5-397B-A17BOpen weights | $0.17 | $1.03 | View |
Qwen | Qwen3.8-27BOpen weights | $0.17 | $0.50 | View |
Qwen | Qwen3-235B-A22B Instruct (2507)Open weights | $0.20 | $0.59 | View |
Qwen | Qwen3-VL-30B-A3B InstructOpen weights | $0.20 | $0.70 | View |
Qwen | Qwen3-VL-Plus | $0.20 | $1.60 | View |
Qwen | Qwen3.8-Flash-NextOpen weights | $0.20 | $0.50 | View |
Qwen | Qwen3.6-Flash | $0.25 | $1.50 | View |
Qwen | Qwen-MT-Plus | $0.25 | $0.75 | View |
Qwen | Qwen3.7-Plus | $0.28 | $1.10 | View |
Qwen | Qwen2.5-7B InstructOpen weights | $0.30 | $0.30 | View |
Qwen | Qwen3.5-Plus | $0.36 | $2.21 | View |
Qwen | Qwen3.6-27BOpen weights | $0.41 | $2.48 | View |
Qwen | Qwen3.6-Plus | $0.50 | $3.00 | View |
Qwen | Qwen3.7-Max | $1.25 | $3.75 | View |
Qwen | Qwen3.8-Max | $1.90 | $5.70 | View |
Qwen | Qwen3.8-2.4T-A95BOpen weights | $2.00 | $6.00 | View |
Qwen API cost calculator
Enter the tokens of a typical request to compare what it costs with every model in the table. Not sure how many tokens your prompt has? Paste it into the token calculator.
| Model | Per request | Per month |
|---|---|---|
| Qwen3.7-Flash | $0.00013 | $1.25 |
| Qwen3-30B-A3B FP8 (open weights, third-party host) | $0.00027 | $2.70 |
| Qwen3.5-35B-A3B (open weights, third-party host) | $0.00034 | $3.44 |
| Qwen3.6-35B-A3B (open weights, third-party host) | $0.00035 | $3.50 |
| Qwen3.5-Flash | $0.00036 | $3.64 |
| Qwen3.8-Flash | $0.00037 | $3.74 |
| Qwen3.5-27B (open weights, third-party host) | $0.00052 | $5.16 |
| Qwen3.8-27B (open weights, third-party host) | $0.00059 | $5.90 |
| Qwen3.8-Flash-Next (open weights, third-party host) | $0.00065 | $6.50 |
| Qwen3.5-122B-A10B (open weights, third-party host) | $0.00069 | $6.89 |
How Qwen API pricing works
Qwen bills its API per token, with separate prices for input tokens (your prompt) and output tokens (the generated answer). The table shows standard rates per 1 million tokens; a token is roughly three quarters of an English word.
FAQ
How much does the Qwen API cost?
As of November 17, 2026, Qwen charges from $0.03 to $1.90 per 1M input tokens and from $0.13 to $5.70 per 1M output tokens across the 11 models in the table above. Qwen also publishes 28 open-weight models that you run on your own hardware or through third-party hosts, so their price depends on the host.
What is the cheapest Qwen model?
Qwen3.7-Flash, at $0.03 per 1M input tokens and $0.13 per 1M output tokens. A request with 2,000 input and 500 output tokens costs about $0.00013 with it, so 1,000 such requests cost $0.13.
What is the most expensive Qwen model?
Qwen3.8-Max, at $1.90 per 1M input tokens and $5.70 per 1M output tokens. The same 2,000 input and 500 output token request costs about $0.0067, so pick the smallest model that handles your task well.
Which Qwen model has the largest context window?
Qwen3.7-Flash accepts up to 1M tokens of context. Long prompts are billed as input tokens, so filling the whole window costs about $0.03 per request.
Is Qwen cheaper than other LLM APIs?
At the low end, yes: Qwen3.7-Flash is cheaper than the cheapest model from any other provider we track, OpenAI GPT-5 Nano ($0.05 input, $0.40 output per 1M tokens). Compare quality, context window, and rate limits too in the LLM price comparison.
How do I estimate the cost of my prompts?
Count the tokens of a typical prompt and answer with the token calculator, then enter them in the cost calculator above to see the price per request and per month for every Qwen model.
