Skip to main content

Qwen3.5 Plus 2026-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

Input / output price
$0.26 / $1.56 per 1M
Context
1M tokens
Released
Feb 15, 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 "qwen/qwen3.5-plus-2026-02-15".

Read docs

Providers

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

ProviderInputOutput
Qwenqwen/qwen3.5-plus-2026-02-15
$0.40/M$2.40/M
OpenRouteropenrouter/qwen3.5-plus-02-15
$0.26/M$1.56/M

Is a provider down? OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.33 per 1M
Average output
$1.98 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.40/MQwenLowest$0.26/MOpenRouter

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

27tokens/sacross providers

Faster than 47% of the other 599 models on the gateway

Response latency

Lower is better

3.4sacross providers

Faster than 40% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 7 published scores from 3 sources, each linked to where it was published.

19.0/ 100

Respan Index#136 of 176

176 ranked models. The shaded band is this model's 95% interval, 14.2 to 26.2. NVIDIA Nemotron 3 Super 120B-A12B and DeepSeek V3.1 fall inside it, so the gap is within the margin of error.
Qwen3.5 Plus 2026-02-15 by category: Coding 6.7 (estimated), Agents 4.2, Reasoning 27.7, Knowledge & language 25.3, Human preference 45.2 (estimated)
  1. 136Qwen3.5-Plus19.0
  2. 135NVIDIA Nemotron 3 Super 120B-A12B19.1
  3. 137DeepSeek V3.118.9

Published scores

BenchmarkScore
Vending-Bench 2Andon Labs0.54 · #64 of 68

Compare Qwen3.5 Plus 2026-02-15: Qwen3.5-Plus vs Qwen3.6-Plus, Qwen3.5-Plus vs Qwen3.8-Max, Qwen3.5-Plus vs Qwen3.8-Flash-Next, Qwen3.5-Plus vs Qwen3.7-Max, Qwen3.5-Plus vs Qwen3.8 27B, Qwen3.5-Plus vs Qwen3.6-Max-Preview

Apps

Use Qwen3.5 Plus 2026-02-15 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.

Qwen3.5 Plus 2026-02-15 FAQ

Short answers, built from the data on this page.

Qwen3.5 Plus 2026-02-15 is a model from Qwen, released on Feb 15, 2026. The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

On the Respan gateway, Qwen3.5 Plus 2026-02-15 costs from $0.26 per 1M input tokens and $1.56 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 2 providers, it costs $0.33 per 1M input tokens and $1.98 per 1M output tokens.

Qwen3.5 Plus 2026-02-15 is available through 2 providers: Qwen and OpenRouter.

Qwen3.5 Plus 2026-02-15 accepts up to 1M 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 "qwen/qwen3.5-plus-2026-02-15". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen3.5 Plus 2026-02-15 scores 19.0 out of 100 on the Respan Index v1.1, ranking #136 of 176 models. By category: Coding 6.7 (estimated), Agents 4.2, Reasoning 27.7, Knowledge & language 25.3, and Human preference 45.2 (estimated). The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Qwen3.5 Plus 2026-02-15 has 7 published benchmark scores, including Vending-Bench 2 0.54, GPQA Diamond 84.8%, and OTIS Mock AIME 2024-2025 86.7%. 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.