impulse

Qwen3 14B

Open weights

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue.

API id Qwen3-14BReleased 28 Apr 2025 (Apr 2025)
Input / 1M
$0.08
at Nebius AI Studio
Output / 1M
$0.24
at Nebius AI Studio
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
3
3 listings
Released
Apr 2025
28 Apr 2025

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.08$0.24

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$42.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$47.04
  • Coding agent1,000 requests a day, 40K in / 2K out$110
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$250
Use your own numbers

Where to run it

3 hosts serve Qwen3 14B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Qwen3-14B
$0.08 / $0.24
DeepInfraInference
Qwen3-14B
$0.12 / $0.24
+25% vs headline
Fireworks AIInference
qwen3-14b
$0.20 / $0.20
+67% vs headline

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
Open weights
License: Apache-2.0
Runs in about 35.4 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 Nebius AI Studio.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Nemotron 3.5 Lightning
    NVIDIA · on Nebius AI Studio
    $0.06 / $0.24
    Has every key capability
    13% less
  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    17% less
  • Qwen3.5 9B
    Alibaba Qwen · on EmpirioLabs AI
    $0.09 / $0.13
    Has every key capability
    17% less
  • Ministral 3B 2512
    Mistral AI · on Mistral AI
    $0.10 / $0.10
    Has every key capability
    17% less

Model line

Newer and older versions, at each lab's own price.

  1. Apr 2025Qwen3 14BLatest$0.08 / $0.24
  2. Apr 2025Qwen 3 14B$0.08 / $0.24
  3. UndatedQwen2.5 14B$0.20 / $0.20

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/Qwen3-14B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 14B cost?

On Nebius AI Studio, Qwen3 14B costs $0.08 per million input tokens and $0.24 per million output tokens.

Which APIs offer Qwen3 14B?

Qwen3 14B runs on 3 APIs: Nebius AI Studio, DeepInfra and Fireworks AI.

What is Qwen3 14B's context window?

33K tokens, with up to 33K tokens in one reply.

Is Qwen3 14B being retired?

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

Is there a newer version of Qwen3 14B?

No. Qwen3 14B is the newest model in its line.

What are cheaper alternatives to Qwen3 14B?

Models that cost less and keep most of what it can do: Nemotron 3.5 Lightning on Nebius AI Studio (13% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Qwen3 14B released?

Alibaba Qwen released it on 28 Apr 2025.

What is Qwen3 14B's API model id?

Use Qwen3-14B with Nebius AI Studio. Other hosts use their own ids: qwen3-14b on Fireworks AI.

Sources

Raw catalog entry for Qwen3-14B on Nebius AI Studio
{
  "max_input_tokens": 32768,
  "max_output_tokens": 32768,
  "input_cost_per_token": 8e-8,
  "output_cost_per_token": 2.4e-7,
  "litellm_provider": "nebius",
  "mode": "chat",
  "supports_function_calling": true,
  "source": "https://nebius.com/prices"
}