How much does the Qwen3.8 2.4T A95B API cost?

On FastMetal, Qwen3.8 2.4T A95B is billed per token: $2.20 per 1M input tokens and $6.60 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Qwen3.8 2.4T A95B with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "qwen3.8-2.4t-a95b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Qwen3.8 2.4T A95B?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Qwen3.8 2.4T A95B?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Qwen

qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

8/12/2026

1,048,576 tokens

Input: $2.20/M

Output: $6.60/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

min_p

presence_penalty

reasoning

reasoning_effort

repetition_penalty

response_format

seed

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Max Output Tokens

262,144

Reasoning Configuration

Default: Thinking on (effort: xhigh)
Selectable effort levels: xhigh
medium
low
Turning thinking off: Not possible (always thinks)

How to control thinking, and what it costs

Data policy

Prompt retention: Not retained — every host this model runs on is configured not to retain prompts
Training: Not used for training

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Measured performance

Time to first response (p50)1.4s

Throughput (p50)244 tokens/s

Routed across 3 independent backends

Measured through FastMetal's own gateway over the last 30 days (713 first-response samples).

Throughput is sampled once a day: the median of 23 observations over the last 30 days.

Time to first response is measured to the first streamed chunk; throughput counts all output tokens, including reasoning tokens. These are observations, not a performance guarantee.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen3.8-2.4t-a95b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Qwen3.8 2.4T A95B actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

To count the number of **“r”**s in **“strawberry”**, spell it out letter by letter: **s t r a w b e r r y** Now check each letter: 1. s — not r 2. t — not r 3. r — yes, count 1 4. a — not r 5. w — not r 6. b — not r 7. e — not r 8. r — yes, count 2 9. r — yes, count 3 10. y — not r So there are **3** “r”s in **strawberry**.

1.3s response203 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

The error happens because `users` is `undefined` when React tries to render this line: ```js {users.map(user => <li key={user.id}>{user.name}</li>)} ``` JavaScript cannot call `.map()` on `undefined`. In your component: ```js function UserList({ users }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` React expects `users` to be an array, but something is rendering `<UserList />` without providing a valid `users` prop. --- ## Common causes ### 1. The parent component is not passing `users` For example: ```js <UserList /> ``` Instead of: ```js <UserList users={users} /> ``` --- ### 2. The data has not loaded yet If `users…

10.9s response1318 output tokens

Professional Email

Write a professional email to a client explaining that the project delivery will be delayed by two weeks due to unexpected technical challenges discovered during integration testing. The tone should be apologetic but con…

Subject: Updated Project Timeline – Revised Delivery Date Dear [Client Name], I hope this message finds you well. I’m writing to provide an important update regarding the delivery timeline for [Project Name]. During our recent integration testing phase, we identified several unexpected technical challenges that require additional resolution to ensure the final deliverable meets the quality and performance standards we committed to. After carefully reviewing the scope of these items with our technical team, we have determined that the project delivery will need to be extended by two weeks. I sincerely apologize for any inconvenience this may cause. Please be assured that we are taking imm…

4.6s response449 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Qwen3.8 2.4T A95B API cost?: On FastMetal, Qwen3.8 2.4T A95B is billed per token: $2.20 per 1M input tokens and $6.60 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Qwen3.8 2.4T A95B with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "qwen3.8-2.4t-a95b" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Qwen3.8 2.4T A95B?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Qwen3.8 2.4T A95B?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.