Context
41K
Max output
41K
Serving providers
4
Cheapest input
$0.08 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
60 t/s
tokens / second
Time to first token
2.69s
latency
Headline indices
13.8
of 100
1.9
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy96.7reasoning: true
GDPval235.8reasoning: true
GPQA Diamond60%reasoning: true
Humanity's Last Exam5%reasoning: true
IFBench41%reasoning: true
LiveCodeBench52%reasoning: true
Long-Context Reasoning0%reasoning: true
MMLU-Pro77%reasoning: true
Omniscience-49.0reasoning: true
Omniscience Accuracy0.2reasoning: true
Omniscience Non Hallucination0.2reasoning: true
SciCode32%reasoning: true
TerminalBench Hard5%default
TerminalBench v2.15%reasoning: true
τ-bench Banking6%reasoning: true
τ²-bench35%reasoning: true

Pricing detail

cost beyond the standard rate · source: models.dev
Reasoning tokens
$4.20
per 1M · thinking output

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.08 to $0.20 per 1M tokens across 4 providers, so the dearest route costs 150% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
NebiusCheapest$0.08$0.241
ComponentUnitStandardBatchCached
Text input/1M tok$0.0800
Text output/1M tok$0.2400
DeepInfra$0.12$0.241
OpenRouter$0.12$0.241
Fireworks AI$0.20$0.201

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300Jul 30Mar 3Jul 20Aug 28$0.200$0.080

Cost calculator

estimate your monthly spend on this model
$35
estimated / month

Model IDs

copy the exact identifier for your platform
nebius/Qwen/Qwen3-14Bdeepinfra/Qwen/Qwen3-14Bqwen/qwen3-14bfireworks_ai/accounts/fireworks/models/qwen3-14b

Frequently asked questions

Qwen3 14B pricing, context and availability

How much does Qwen3 14B cost?

Qwen3 14B costs $0.08 per 1M input tokens and $0.20 per 1M output tokens at its cheapest provider via Nebius. Across 4 serving providers, input prices range from $0.08 to $0.20 per 1M tokens.

What is the context window of Qwen3 14B?

Qwen3 14B accepts up to 41K tokens of context and can return up to 41K output tokens.

Which providers serve Qwen3 14B?

Qwen3 14B is available from 4 serving providers, each with its own pricing and model ID. Nebius is currently the cheapest.

What can Qwen3 14B do?

Qwen3 14B supports tool use.

Other Alibaba models

compare pricing across the Alibaba lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI