Qwen3 Coder

Qwen3 Coder (alibaba via OpenCode) costs $0.45 per 1M input tokens and $1.80 per 1M output tokens, as last published by OpenCode.

Qwen3 Coder has a context window of 262,144 tokens (the maximum combined input and output it can handle in a single request).

Qwen3 Coder sits in the large size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.

Qwen3 Coder can generate up to 65,536 tokens in a single response. Reasoning (thinking) tokens count toward this limit.

Qwen3 Coder's training data runs through April 2025, so it may not know about later events. Coolhand records the cutoff at month precision, since providers often publish only the month.

Qwen3 Coder accepts text as input and produces text as output, as recorded in the Coolhand catalog.

Yes — the weights of Qwen3 Coder can be downloaded under the Apache-2.0 license. Check the license terms for any limits on commercial use.

Yes — alibaba deprecated Qwen3 Coder on August 17, 2026. Listed as deprecated on OpenCode Zen, model 'Qwen3 Coder 480B', deprecation date February 6, 2026.

alibaba retired Qwen3 Coder on August 17, 2026.

Since Qwen3 Coder is deprecated, alibaba customers are moving to Qwen3 235B A22B 2507, Qwen3 32B (dense), and Qwen3 Coder 30B A3B Instruct.

Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=opencode&q[model_eq]=qwen3-coder — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.

Coolhand also tracks Qwen3.6 Plus Free, Qwen3 235B A22B 2507, Qwen3 32B (dense), Qwen3 Coder 30B A3B Instruct, Qwen3.5 Plus, and Qwen3.6 Plus from alibaba. Some may already be deprecated, so check each model's status alongside its current pricing.