Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

Qwen/Qwen3.8-2.4T-A95B pricing

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, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows. Qwen/Qwen3.8-2.4T-A95B from DeepInfra costs $2.00 per 1M input tokens and $6.00 per 1M output tokens. Cached input is $0.200 per 1M. Context window 262,144 tokens.

API id Qwen/Qwen3.8-2.4T-A95B · DeepInfra · source · updated 2026-09-25 · general-purpose

$2.00
Input / 1M tokens
$6.00
Output / 1M tokens
$0.200
Cached input / 1M
262K
Context window

Qwen/Qwen3.8-2.4T-A95B specifications

Provider
DeepInfra
API id
Qwen/Qwen3.8-2.4T-A95B
Model type
general-purpose
Context window
262K tokens
Max output
not published
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Qwen3.8 2.4T A95B across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
Alibaba (Qwen)VendorCheapest
$2.00$0.250$6.00$8.00—
DeepInfraHostviewing
$2.00$0.200$6.00$8.00—
$2.00$0.250$6.00$8.00—
$2.00$0.250$6.00$8.00—

What Qwen/Qwen3.8-2.4T-A95B costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0050
Document summary50,0002,000$0.11
1M tokens in, 200K out1,000,000200,000$3.20

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does Qwen/Qwen3.8-2.4T-A95B cost per 1M tokens?
Qwen/Qwen3.8-2.4T-A95B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on the standard tier. Cached input is $0.200 per 1M.
What is Qwen/Qwen3.8-2.4T-A95B's context window?
Qwen/Qwen3.8-2.4T-A95B accepts up to 262,144 tokens in a single request.
Is there a cheaper DeepInfra model than Qwen/Qwen3.8-2.4T-A95B?
Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $2.00 for Qwen/Qwen3.8-2.4T-A95B, with a 1,048,576 token context window.
Where does this Qwen/Qwen3.8-2.4T-A95B price come from?
From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Other DeepInfra models

See all DeepInfra pricing →