Qwen3 Coder 480B A35B qwen/qwen3-coder
Served by 10 providers. Cheapest: Hyperbolic at $0.40 blended /1M tokens. The most expensive listing costs 7.5× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Hyperbolic Qwen/Qwen3-Coder-480B-A35B-Instruct |
Inference hosts | $0.40 | $0.40 | — | $0.40 | 262k | Docs list a single "$0.40/M tokens" price (no input/output split). Inference docs section is marked hidden/noindex; availability should be re-verified. |
◐ src 2026-09-18 |
| DeepInfra Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo |
Inference hosts | $0.30 | $1 | $0.10 | $0.475 | 262k | fp4 Turbo deployment (fp4). |
✓ src src2 2026-09-18 |
| OpenRouter qwen/qwen3-coder |
LLM routers | $0.30 | $1 | $0.10 | $0.475 | 262k | api modality text->text |
✓ src 2026-09-18 |
| Google Vertex AI (Gemini Enterprise Agent Platform) | Hyperscaler AI platforms | $0.22 | $1.80 | $0.022 | $0.615 | — | batch −50% Managed MaaS API. Batch $0.11/$0.90. |
✓ src 2026-09-18 |
| Venice.ai API qwen3-coder-480b-a35b-instruct-turbo |
Inference hosts | $0.35 | $1.50 | $0.04 | $0.637 | 256k | fp8 Venice serves the "Turbo" variant of Qwen3-Coder-480B-A35B. |
✓ src src2 2026-09-18 |
| Featherless Qwen/Qwen3-Coder-480B-A35B-Instruct |
Inference hosts | $0.38 | $1.55 | $0.076 | $0.673 | 33k | Developer-plan per-token rate; model_class qwen3-coder-480b; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Novita AI qwen/qwen3-coder-480b-a35b-instruct |
Inference hosts | $0.38 | $1.55 | — | $0.673 | 262k |
✓ src src2 2026-09-18 |
|
| Amazon Bedrock qwen.qwen3-coder-480b-a35b-v1:0 |
Hyperscaler AI platforms | $0.45 | $1.80 | — | $0.788 | 128k | batch −50% |
✓ src src2 2026-09-18 |
| GMI Cloud Inference Engine Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 |
Inference hosts | $0.90 | $4.50 | — | $1.80 | — | fp8 from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) |
✓ src src2 2026-09-18 |
| Alibaba Cloud Model Studio (Qwen API, International) qwen3-coder-480b-a35b-instruct |
Model labs | $1.50 | $7.50 | — | $3 | — | Singapore/International price. 32K-128K: $2.7/$13.5; 128K-200K: $4.5/$22.5. |
✓ src 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.