Skip to main content

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
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen3-coder-next".

Read docs

Providers

4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Parasailparasail/qwen3-coder-next
$0.12/M$0.80/M
Featherlessfeatherless/qwen3-coder-next
$0.16/M$1.15/M
Concentrateconcentrate/qwen3-coder-next
$0.50/M$1.20/M
OpenRouteropenrouter/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.

Highest$0.50/MConcentrateLowest$0.12/MParasail and OpenRouter

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 better

18tokens/sacross providers

Faster than 34% of the other 599 models on the gateway

Response latency

Lower is better

1.6sacross providers

Faster than 56% of the other 780 models on the gateway

Benchmarks

4 published scores from 2 sources, each linked to where it was published.

Published scores

BenchmarkScore
SWE-bench Verifiedhuggingface.co70.6%
SWE-Bench Prohuggingface.co44.3%
Terminal-Bench 2.0huggingface.co36.2%
WeirdMLHåvard Tveit Ihle34.4%

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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.