Model Library
AlibabaReleased February 3, 2026Qwen3 Coder Next
Alibaba · Released February 3, 2026
Intelligence score
21
At a glance
- Intelligence
- 21
- Speed
- 88.5tokens/sec
- Latency
- 1.91stime to first token
- Input price
- $0.35per 1M tokens
- Output price
- $1.20per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 79.7billions
Summary
Comparison summary
Qwen3 Coder Next scores 21 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7). Qwen3 Coder Next generates output at 88.5 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s). Qwen3 Coder Next costs $0.35 per 1M input tokens (better than average, median: $0.53) and $1.20 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Qwen3 Coder Next |
|---|---|
| Provider | Alibaba |
| Release date | February 3, 2026 |
| Intelligence score | 21 |
| Speed | 88.5 tokens/sec |
| Latency (TTFT) | 1.91s |
| Input price | $0.35 / 1M tokens |
| Output price | $1.20 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 79.7B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-coder-next |
Pricing
Token prices
Price per 1M tokens
Qwen3 Coder Next, as listed in the catalog record
- Input$0.35
- Output$1.20
| Token type | Price per 1M |
|---|---|
| Input | $0.35 |
| Output | $1.20 |
Model Intelligence legacy profile: qwen3-coder-next
FAQ · 21
Frequently asked questions
Qwen3 Coder Next was released on February 3, 2026.
Qwen3 Coder Next was created by Alibaba.
Qwen3 Coder Next scores 21 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 7).
Qwen3 Coder Next generates output at 88.5 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 81.5 t/s).
Qwen3 Coder Next has a time to first token (TTFT) of 1.91s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.59s).
Qwen3 Coder Next costs $0.35 per 1M input tokens (better than average, median: $0.53) and $1.20 per 1M output tokens (better than average, median: $1.05), based on the median across providers serving the model.
Qwen3 Coder Next costs $0.35 per 1M input tokens and $1.20 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.43 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Qwen3 Coder Next generated 32M output tokens, which is at the higher end compared to other open weight non-reasoning models of similar size (median: 9.2M).
No, Qwen3 Coder Next is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Coder Next supports text input.
Qwen3 Coder Next supports text output.
No, Qwen3 Coder Next does not support image input. It can only process text.
No, Qwen3 Coder Next is not multimodal. It only supports text input.
Qwen3 Coder Next has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 Coder Next is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Coder Next has 79.7 billion parameters (3 billion active).
Qwen3 Coder Next is a Mixture of Experts (MoE) model with 79.7 billion total parameters, but only 3 billion active parameters are used during inference.
Qwen3 Coder Next is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 Coder Next achieves a score of 21 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Coder Next is available via API through 4 providers.
Qwen3 Coder Next is available through 4 API providers.