LiteLLMModels

Qwen35 122B A10B API Pricing

As of October 10, 2026, Qwen35 122B A10B costs $0.22 per 1M input tokens and $2.20 per 1M output tokens on Databricks, with cache reads at $0.22 and cache writes at $0.22 per 1M tokens. It has a 262,144-token context window and returns up to 25,000 tokens per response.

By AlibabaModel ID databricks/databricks-qwen35-122b-a10bPrices updated Checked
Input
$0.22 / 1M tokens
Output
$2.20 / 1M tokens
Cache read
$0.22 / 1M tokens
Context window
262,144 tokens
Max output
25,000 tokens
Providers
1
Added to LiteLLM
September 4, 2026

Qwen35 122B A10B pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Databricksdatabricks/databricks-qwen35-122b-a10b$0.22$2.20$0.22$0.22256K

What Qwen35 122B A10B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Databricks$1.54

100 long-document requests with 100,000 input and 2,000 output tokens each

Databricks$2.64

Qwen35 122B A10B features

Input: text. Output: text.

Use Qwen35 122B A10B with LiteLLM

Call Qwen35 122B A10B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="databricks/databricks-qwen35-122b-a10b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen35-122b-a10b
    litellm_params:
      model: databricks/databricks-qwen35-122b-a10b
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen35-122b-a10b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen35 122B A10B FAQ

How much does Qwen35 122B A10B cost?

Qwen35 122B A10B costs $0.22 per 1M input tokens and $2.20 per 1M output tokens on Databricks, with cache reads at $0.22 and cache writes at $0.22 per 1M tokens.

What is the context window of Qwen35 122B A10B?

Qwen35 122B A10B has a 262,144-token context window and returns up to 25,000 tokens per response.

Which providers offer Qwen35 122B A10B?

Qwen35 122B A10B is available from Databricks through LiteLLM, using the model name databricks/databricks-qwen35-122b-a10b.

How do I call Qwen35 122B A10B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="databricks/databricks-qwen35-122b-a10b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Qwen35 122B A10B support?

Qwen35 122B A10B supports function calling and reasoning. It does not support image input.

When did LiteLLM add Qwen35 122B A10B?

Qwen35 122B A10B was added to LiteLLM's model price file on September 4, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Databricks.

Provider pages: Databricks.