Model Library
AlibabaReleased July 22, 2025Qwen3 Coder 480B
Alibaba · Released July 22, 2025
Intelligence score
18
At a glance
- Intelligence
- 18
- Speed
- 60.3tokens/sec
- Latency
- 3.12stime to first token
- Input price
- $1.50per 1M tokens
- Output price
- $7.50per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 480billions
Summary
Comparison summary
Qwen3 Coder 480B A35B Instruct scores 18 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 17). Qwen3 Coder 480B A35B Instruct generates output at 60.3 tokens per second (based on Alibaba's API), which is above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). Qwen3 Coder 480B A35B Instruct costs $1.50 per 1M input tokens (at the higher end, median: $0.60) and $7.50 per 1M output tokens (at the higher end, median: $2.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 Coder 480B |
|---|---|
| Provider | Alibaba |
| Release date | July 22, 2025 |
| Intelligence score | 18 |
| Speed | 60.3 tokens/sec |
| Latency (TTFT) | 3.12s |
| Input price | $1.50 / 1M tokens |
| Output price | $7.50 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 480B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-coder-480b-a35b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 Coder 480B, as listed in the catalog record
- Input$1.50
- Output$7.50
| Token type | Price per 1M |
|---|---|
| Input | $1.50 |
| Output | $7.50 |
Model Intelligence legacy profile: qwen3-coder-480b-a35b-instruct
FAQ · 20
Frequently asked questions
Qwen3 Coder 480B A35B Instruct was released on July 22, 2025.
Qwen3 Coder 480B A35B Instruct was created by Alibaba.
Qwen3 Coder 480B A35B Instruct scores 18 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 17).
Qwen3 Coder 480B A35B Instruct generates output at 60.3 tokens per second (based on Alibaba's API), which is above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
Qwen3 Coder 480B A35B Instruct has a time to first token (TTFT) of 3.12s (based on Alibaba's API), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 2.33s).
Qwen3 Coder 480B A35B Instruct costs $1.50 per 1M input tokens (at the higher end, median: $0.60) and $7.50 per 1M output tokens (at the higher end, median: $2.40), based on Alibaba's API.
Qwen3 Coder 480B A35B Instruct costs $1.50 per 1M input tokens and $7.50 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.10 per 1M tokens. Pricing may vary by provider.
No, Qwen3 Coder 480B A35B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 Coder 480B A35B Instruct supports text input.
Qwen3 Coder 480B A35B Instruct supports text output.
No, Qwen3 Coder 480B A35B Instruct does not support image input. It can only process text.
No, Qwen3 Coder 480B A35B Instruct is not multimodal. It only supports text input.
Qwen3 Coder 480B A35B Instruct 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 480B A35B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 Coder 480B A35B Instruct has 480 billion parameters (35 billion active).
Qwen3 Coder 480B A35B Instruct is a Mixture of Experts (MoE) model with 480 billion total parameters, but only 35 billion active parameters are used during inference.
Qwen3 Coder 480B A35B Instruct is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 Coder 480B A35B Instruct achieves a score of 18 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 Coder 480B A35B Instruct is available via API through 8 providers.
Qwen3 Coder 480B A35B Instruct is available through 8 API providers.