OpenRouter describes Qwen3 Coder Next as an open-weight model for coding agents and local development, with a sparse design that activates few parameters per token. Text in, text out. Paste the code. It will not see a screenshot. Qwen3 Coder Next is listed at $0.12 input and $0.80 output per million tokens, with a 262,144-token context window. In: text. Out: text. Tools: Yes. Open weights: Yes.
Tools: Yes.
in text
out text
tools
open weights
Facts
Facts for Qwen3 Coder Next. OpenRouter models API, checked 20 Nov 2026.
Fact
Value
Source
Release date
4 Feb 2026
OpenRouter field created. This is the listing date the feed publishes. Checked 20 Nov 2026.
Context window
262,144 tokens
OpenRouter field context_length. Checked 20 Nov 2026.
Max output
235,929 tokens
OpenRouter field top_provider.max_completion_tokens. Checked 20 Nov 2026.
Input price
$0.12 per million tokens. Published per-token rate 0.00000012.
OpenRouter field pricing.prompt, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Output price
$0.80 per million tokens. Published per-token rate 0.0000008.
OpenRouter field pricing.completion, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Batch input price
No batch route listed
Sibling OpenRouter id ending in :batch, field pricing.prompt. Checked 20 Nov 2026.
Batch output price
No batch route listed
Sibling OpenRouter id ending in :batch, field pricing.completion. Checked 20 Nov 2026.
Input modalities
text
OpenRouter field architecture.input_modalities. Checked 20 Nov 2026.
Output modalities
text
OpenRouter field architecture.output_modalities. Checked 20 Nov 2026.
Tools
Yes
OpenRouter field supported_parameters contains tools. Checked 20 Nov 2026.
OpenRouter field hugging_face_id. Empty means no public weights id is listed, which is not a legal opinion. Checked 20 Nov 2026.
Knowledge cutoff
Unknown
OpenRouter field knowledge_cutoff. Checked 20 Nov 2026.
Reasoning
Unknown
OpenRouter field reasoning. Missing means unknown, not unsupported. Checked 20 Nov 2026.
Other published prices
input_cache_read: 0.00000007 USD
Other OpenRouter pricing fields, shown raw. The documented unit is USD per token, request, or unit — not converted to per million. Checked 20 Nov 2026.
A $0 token price does not mean the model is free to use. Another published price field is non-zero and may be the one you are billed on.
Listing blurb
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
No third-party index was included for this model in the feed. The Best Model For does not fill that gap.
Guide note · 19 Nov 2026
OpenRouter describes Qwen3 Coder Next as an open-weight model for coding agents and local development, with a sparse design that activates few parameters per token. Text in, text out. Paste the code. It will not see a screenshot.
The weights id is the point. Use it when the repository cannot be sent to a hosted flagship. The listing aims it at agent workflows, so give it tools and a narrow goal.
Qwen3 Coder Next is listed at $0.12 input and $0.80 output per million tokens, with a 262,144-token context window.
Draft a migration script from a written plan
Text in, tools listed, a coding brief. Run the script. Do not ship it from the first answer.
Qwen3 Coder Next is listed at $0.12 input and $0.80 output per million tokens, with a 262,144-token context window.
The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.
Qwen3 Coder Next is listed at $0.12 input and $0.80 output per million tokens, with a 262,144-token context window. No batch route is listed. Other price fields, if any, are on this page and are not converted.
Does Qwen3 Coder Next have open weights?
The feed lists a Hugging Face id: Qwen/Qwen3-Coder-Next. That is what The Best Model For means by open weights.
What is Qwen3 Coder Next good for?
OpenRouter describes Qwen3 Coder Next as an open-weight model for coding agents and local development, with a sparse design that activates few parameters per token. Text in, text out. Paste the code. It will not see a screenshot.