Qwen3 Coder 480B A35B Instruct
Qwen3 Coder 480B A35B Instruct is Alibaba's language model with a 262K context window and up to 66K output tokens, available from 7 providers, starting at $0.22 / 1M input and $1.50 / 1M output. Qwen3's flagship agentic code model with 480B total and 35B activated parameters, excelling at autonomous programming, tool calling, and browser-use tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #233 |
| Math Index | #181 |
| MMLU-Pro | #147 |
| GPQA | #320 |
| HLE | #403 |
| LiveCodeBench | #147 |
| AIME | #70 |
| IFBench | #259 |
| Time to First Token | #506 |
| SciCode | #225 |
| MATH-500 | #55 |
| AIME 2025 | #181 |
| LCR | #224 |
| TerminalBench Hard | #156 |
| TAU2 | #207 |
| Output TPS | #168 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | |||
|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
| $1.50 | $7.50 | N/A | $0.75 | $3.75 | |
| $0.4 | $1.60 | N/A | — | — | |
| $0.45 | $1.80 | N/A | — | — | |
| $0.22 | $1.80 | $0.022 | $0.11 | $0.9 | |
| $0.38 | $1.55 | N/A | — | — | |
| $0.38 | $1.55 | N/A | — | — | |
| $1.00 | $1.50 | N/A | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen3 Coder 480B A35B Instruct, ranked by cheapest on-demand price. The model needs about 1152 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_ND96is_MI300X_v5 |  Azure | 8× AMD Instinct MI300X GPU (192GB) | 1536 GB | $48.00/hr | ||
| Standard_ND96isr_MI300X_v5 | Azure | 8× AMD Instinct MI300X | 1536 GB | $48.00/hr | ||
| p6-b200.48xlarge |  AWS | 8× B200 | 1432 GB | $113.93/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MiroThinker 1.7 | — | — | — | — | Available |
| Qwen3 30B A3B Thinking | 262K | $0.200 | $0.900 | Available | |
| Qwen3 Coder 30B A3B Instruct | 262K | $0.070 | $0.270 | Available | |
| Qwen3 30B A3B Instruct | 262K | $0.048 | $0.193 | Available | |
| Qwen3 235B A22B Thinking | 262K | $0.220 | $0.880 | Deprecated | |
| Qwen3 Coder | 262K | $0.300 | $1.00 | Deprecated | |
| Qwen3 235B A22B | 262K | $0.087 | $0.350 | Available | |
| Qwen3 30B A3B | 131K | $0.051 | $0.200 | Deprecated | |
| Qwen3 Coder 480B A35B Instruct | — | 262K | $0.220 | $1.50 | Current |
| Qwen3 235B A22B Instruct | — | 262K | $0.090 | $0.550 | Available |
| KwaiPilot KAT Coder | — | 262K | $0.900 | $0.900 | Available |