Qwen: Qwen3 Coder 480B A35B
by QwenQwen: Qwen3 Coder 480B A35B is a large language model from Qwen. It costs $0.300 per million input tokens and $1.00 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $1.00
- Cached input / 1M
- $0.100
- Context window
- 262K
On repeated prefixes
tokens
Who serves it cheapest
5 hosts serve Qwen3 Coder 480B A35B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfraCheapestfp4 | $0.300 | $1.00 | 262K | - | 96.7% |
| $0.220 | $1.80 | 262K | - | 99.9% | |
| Venicefp8 | $0.350 | $1.50 | 256K | - | 90.3% |
| Novitafp8 | $0.380 | $1.55 | 262K | - | 94.6% |
| Alibaba | $0.975 | $4.88 | 262K | - | 100.0% |
The spread between DeepInfra and Alibaba is 4.1× for identical weights. Quantization and context limits differ, so check both columns before switching.
About Qwen3 Coder 480B A35B
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Specifications
| Model ID | qwen/qwen3-coder |
|---|---|
| Provider | Qwen |
| Context window | 262K tokens |
| Max output | 66K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2025-06-30 |
| Open weights | Yes - Qwen/Qwen3-Coder-480B-A35B-Instruct |
| Released | July 23, 2025 |
Cheaper alternatives
Models that cost less than Qwen3 Coder 480B A35B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Qwen: Qwen3 Coder 480B A35B cost?
$0.300 per million input tokens and $1.00 per million output tokens. Cached input reads cost $0.100 per million tokens.
What is the context window of Qwen: Qwen3 Coder 480B A35B?
262K tokens, with up to 66K tokens of output per request.
Which provider serves Qwen: Qwen3 Coder 480B A35B cheapest?
DeepInfra at $0.300 per million input tokens - 4.1× cheaper than Alibaba, the most expensive of the 5 hosts serving it.
Confirm against the source: Qwen official pricing.