LiteLLMModels

Qwen3 30B A3B Thinking 2507 API Pricing

As of October 10, 2026, Qwen3 30B A3B Thinking 2507 costs $0.90 per 1M input tokens and $0.90 per 1M output tokens on Fireworks AI. It has a 262,144-token context window and returns up to 262,144 tokens per response.

By AlibabaModel ID fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507Prices updated Checked
Input
$0.90 / 1M tokens
Output
$0.90 / 1M tokens
Context window
262,144 tokens
Max output
262,144 tokens
Providers
1
Added to LiteLLM
December 2025

Qwen3 30B A3B Thinking 2507 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 LiteLLMInputOutputContext
Fireworks AIfireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507$0.90$0.90256K

What Qwen3 30B A3B Thinking 2507 costs in practice

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

Fireworks AI$2.25

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

Fireworks AI$9.18

Use Qwen3 30B A3B Thinking 2507 with LiteLLM

Call Qwen3 30B A3B Thinking 2507 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="fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3-30b-a3b-thinking-2507
    litellm_params:
      model: fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507
      api_key: os.environ/FIREWORKS_AI_API_KEY
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": "qwen3-30b-a3b-thinking-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 30B A3B Thinking 2507 FAQ

How much does Qwen3 30B A3B Thinking 2507 cost?

Qwen3 30B A3B Thinking 2507 costs $0.90 per 1M input tokens and $0.90 per 1M output tokens on Fireworks AI.

What is the context window of Qwen3 30B A3B Thinking 2507?

Qwen3 30B A3B Thinking 2507 has a 262,144-token context window and returns up to 262,144 tokens per response.

Which providers offer Qwen3 30B A3B Thinking 2507?

Qwen3 30B A3B Thinking 2507 is available from Fireworks AI through LiteLLM, using the model name fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507.

How do I call Qwen3 30B A3B Thinking 2507 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", 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.

When did LiteLLM add Qwen3 30B A3B Thinking 2507?

Qwen3 30B A3B Thinking 2507 was added to LiteLLM's model price file in December 2025.

Sources

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

LiteLLM docs: Fireworks AI.

Provider pages: Fireworks AI.