Qwen
Qwen3 Coder Next
Released 2026-02-04
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...
You send / 1M
$0.120
tokens in
It replies / 1M
$0.800
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0006
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Parasail · bf16 | $0.120 | $0.800 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 236K tokens
- Repeated text is billed at $0.070 per 1M (prompt caching)
- Intelligence score: 9.2 / 100 (Artificial Analysis)
Similar models
- Skyfall 36B V2Thedrummer · $0.550 in / $0.800 out per 1M
- Qwen-PlusQwen · $0.260 in / $0.780 out per 1M
- Llama 3.1 Euryale 70B v2.2Sao10k · $0.850 in / $0.850 out per 1M
- Weaver (alpha)Mancer · $0.400 in / $0.750 out per 1M
- Codestral 2508Mistral · $0.300 in / $0.900 out per 1M
- UncensoredCognitivecomputations · $0.200 in / $0.900 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models