Qwen3 Coder Next
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. $0.11 per million input tokens, $0.80 per million output tokens. 262,144 token context window, maximum output of 262,144 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $0.12 / $0.80 per 1M
- Context
- 262K tokens
- Released
- Feb 3, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Parasail parasail/qwen3-coder-next | $0.12/M | $0.80/M |
Featherless featherless/qwen3-coder-next | $0.16/M | $1.15/M |
Concentrate concentrate/qwen3-coder-next | $0.50/M | $1.20/M |
OpenRouter openrouter/qwen3-coder-next | $0.12/M | $0.80/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.23 per 1M
- Average output
- $0.99 per 1M
- Average cache read
- $0.21 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better18tokens/sacross providers
Response latency
Lower is better1.6sacross providers
Benchmarks
4 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench Verifiedhuggingface.co | 70.6% | huggingface.co | Feb 3, 2026 |
| SWE-Bench Prohuggingface.co | 44.3% | huggingface.co | Feb 3, 2026 |
| Terminal-Bench 2.0huggingface.co | 36.2% | huggingface.co | Feb 3, 2026 |
| WeirdMLHåvard Tveit Ihle | 34.4% | Håvard Tveit Ihle | Oct 5, 2026 |
Apps
Use Qwen3 Coder Next in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen3 Coder Next FAQ
Short answers, built from the data on this page.
Qwen3 Coder Next is a model from Qwen, released on Feb 3, 2026. Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. $0.11 per million input tokens, $0.80 per million output tokens. 262,144 token context window, maximum output of 262,144 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, Qwen3 Coder Next costs from $0.12 per 1M input tokens and $0.80 per 1M output tokens on Parasail and OpenRouter, after gateway discounts. Averaged across its 4 providers, it costs $0.23 per 1M input tokens and $0.99 per 1M output tokens.
Qwen3 Coder Next is available through 4 providers: Parasail, Featherless, Concentrate, and OpenRouter.
Qwen3 Coder Next accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-coder-next". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3 Coder Next has 4 published benchmark scores, including SWE-bench Verified 70.6%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.