NVIDIA NIM logo

qwen3.5-122b-a10b API status on NVIDIA NIM

Check provider
Available from NVIDIA NIM
★★★★★★★★★★ 3.5 Benchmark-backed score

Qwen vision-language model for visual reasoning, documents, and agent tasks

Check providerOpenAI compatibleReasoningTool callingJSON modeTextImage
Check Provider Compare Save API Key
API Details

Copy-ready connection details

Use these values in your client or SDK.
Base URL
https://integrate.api.nvidia.com/v1
Model ID
qwen/qwen3.5-122b-a10b
API format OpenAI Chat Completions
Technical Details

qwen3.5-122b-a10b specifications

Provider and model catalog
Context window 262K
Max output 66K
Status Check provider
Family qwen
Released Feb 23, 2026
Last updated Jul 18, 2026
Free listing since Feb 24, 2026
Input text, image, video, audio
Output text
Capabilities reasoning, tool calling, structured output, file attachments, temperature control
Open weights Yes
Weights Hugging Face

External benchmark references

Benchmark Score Metric Date
SWE-Bench Verified 72 resolved Not listed
AI Recommendation

Should you use qwen3.5-122b-a10b?

qwen3.5-122b-a10b is listed for chat workloads and supports a 262K context window.

Check NVIDIA NIM's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.

Best for
  • Chat
Strengths & Weaknesses

Strengths

  • Long context window
  • Reasoning mode listed
  • Tool calling support
  • Structured JSON output

Watch outs

  • Current endpoint availability needs provider confirmation
  • Free-tier rate limits apply
Benchmark Overview

Benchmark signals for qwen3.5-122b-a10b

Measured data
Intelligence General reasoning and instruction following
32.3/100
Coding Programming and code generation
45.7/100
Agentic Tool use and multi-step tasks
20.7/100
Speed Observed generation speed
135 tok/s
Context Maximum listed context window
262K
Pricing

qwen3.5-122b-a10b pricing per 1M tokens

Check provider
Input $0.4 per 1M tokens
Output $3.2 per 1M tokens
Free access Check provider NVIDIA NIM
Rate limit Up to 40 RPM provider policy
Typical Use Cases

qwen3.5-122b-a10b use cases

Chat

qwen3.5-122b-a10b is tagged for chat in this catalog and works with OpenAI-compatible client libraries.

FAQ

qwen3.5-122b-a10b free API FAQ

Is qwen3.5-122b-a10b free to use?

qwen3.5-122b-a10b appears in the free model catalog for NVIDIA NIM, but its current endpoint availability should be confirmed with the provider before use.

What is the qwen3.5-122b-a10b model ID?

The model ID shown in this catalog is qwen/qwen3.5-122b-a10b.

What are the qwen3.5-122b-a10b free tier rate limits on NVIDIA NIM?

The listed free tier limit is Up to 40 RPM. Limits can change per account tier, so confirm against the provider dashboard.

What context window does qwen3.5-122b-a10b support?

The listed context window is 262K tokens with up to 66K output tokens.

Related Models

Related free models similar to qwen3.5-122b-a10b

View all models
Qwen/Qwen3.5-122B-A10B ModelScope · 8K · Free tier 01-ai/yi-large NVIDIA NIM · 131K · Free tier adept/fuyu-8b NVIDIA NIM · 131K · Free tier ai21labs/jamba-1.5-large-instruct NVIDIA NIM · 131K · Free tier aisingapore/sea-lion-7b-instruct NVIDIA NIM · 131K · Free tier baai/bge-m3 NVIDIA NIM · 131K · Free tier

More about qwen3.5-122b-a10b

Qwen3.5 122B (10B active via MoE) is Alibaba's large MoE model, free on NVIDIA NIM with up to 40 RPM and no daily token cap. The massive expert pool delivers broad knowledge and strong reasoning while keeping inference efficient with only 10B active parameters. OpenAI-compatible API. Requires NVIDIA Developer Program membership and phone verification.

For API keys, setup steps, and provider-level limits, see the NVIDIA NIM provider page.