Qwen3 Coder 480B A35B
The cheapest provider for Qwen3 Coder 480B A35B is DeepInfra at $0.475 per 1M tokens (blended), charging $0.30 per 1M input and $1.00 per 1M output tokens. 5 providers serve it; the most expensive charges 4.1× as much. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.475
at DeepInfra
Input / output
$0.30 / $1.00
per 1M tokens
Providers
5
4.1× spread
7 days
—
best price
30 days
—
best price
Context
256K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp4 | $0.30 | $1.00 | $0.475 | best | |||
Googleus-south1 | $0.22 | $1.80 | $0.615 | +29% | |||
| fp8 | $0.35 | $1.50 | $0.638 | +34% | |||
| fp8 | $0.38 | $1.55 | $0.673 | +42% | |||
Alibabaopensource | $0.975 | $4.875 | $1.95 | +311% |
- DeepInfraCheapestturbo$0.475$0.30 in · $1.00 outbest256K ctx97.7% uptimefp4
- us-south1$0.615$0.22 in · $1.80 out+29%256K ctx99.9% uptime
- $0.638$0.35 in · $1.50 out+34%250K ctx93.2% uptimefp8
- $0.673$0.38 in · $1.55 out+42%256K ctx93.2% uptimefp8
- opensource$1.95$0.975 in · $4.875 out+311%256K ctx100% uptime
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Long-context pricing
Higher rates once the prompt passes a size threshold.
| Offered by | Prompt size | Input | Output |
|---|---|---|---|
| Alibaba (opensource) | base | $0.975 | $4.875 |
| > 32K | $1.755 | $8.775 | |
| > 125K | $2.925 | $14.63 |
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| DeepInfra (turbo) | $0.10 |
| Venice | $0.04 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
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...
- Released
- Jul 23, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-coder-480b-a35b-07-25
- Weights
- Qwen/Qwen3-Coder-480B-A35B-Instruct