impulse

Qwen3 235B A22B 2507

Open weights

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.

API id qwen.qwen3-235b-a22b-2507-v1:0Released 21 Jul 2025 (Jul 2025)
Input / 1M
$0.22
at Amazon Bedrock
Output / 1M
$0.88
at Amazon Bedrock
Context window
262K
tokens
Max output
8K
tokens per reply
Hosts
1
2 listings
Released
Jul 2025
21 Jul 2025

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.22$0.88
Batch
50% off
$0.11$0.44
Flex
50% off
$0.11$0.44

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$132
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$137
  • Coding agent1,000 requests a day, 40K in / 2K out$317
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$370
Use your own numbers

Where to run it

1 host serve Qwen3 235B A22B 2507. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
qwen.qwen3-235b-a22b-2507-v1:0
$0.22 / $0.88
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
qwen.qwen3-235b-a22b-2507
$0.22 / $0.88

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Native structured output
Open weights
License: Apache-2.0
Runs in about 564.2 GB of GPU memory
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Amazon Bedrock.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    48% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    48% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    32% less

Open-weight picks

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/qwen.qwen3-235b-a22b-2507-v1:0",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 235B A22B 2507 cost?

On Amazon Bedrock, Qwen3 235B A22B 2507 costs $0.22 per million input tokens and $0.88 per million output tokens.

Which APIs offer Qwen3 235B A22B 2507?

Qwen3 235B A22B 2507 runs on 1 API: Amazon Bedrock.

What is Qwen3 235B A22B 2507's context window?

262K tokens, with up to 8K tokens in one reply.

Is Qwen3 235B A22B 2507 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Qwen3 235B A22B 2507?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (48% less), GPT-6 Luna on OpenAI (48% less) and Qwen3.5 397B A17B on AIHubMix (4% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Qwen3 235B A22B 2507 released?

Alibaba Qwen released it on 21 Jul 2025.

What is Qwen3 235B A22B 2507's API model id?

Use qwen.qwen3-235b-a22b-2507-v1:0 with Amazon Bedrock.

Sources

Raw catalog entry for qwen.qwen3-235b-a22b-2507-v1:0 on Amazon Bedrock
{
  "input_cost_per_token": 2.2e-7,
  "input_cost_per_token_flex": 1.1e-7,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 262144,
  "max_output_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 8.8e-7,
  "output_cost_per_token_flex": 4.4e-7,
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_tool_choice": true,
  "supports_native_structured_output": true,
  "input_cost_per_token_batches": 1.1e-7,
  "output_cost_per_token_batches": 4.4e-7,
  "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html"
}