LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen2.5-Coder-32B-Instruct

alibaba·alibaba/qwen2.5-coder-32b-instruct·Deprecated·Open weights·qwen series
Open coding-focused Qwen model for code generation, repair, and repository reasoning

Qwen2.5-Coder-32B-Instruct by alibaba is offered by 9 providers on this page. Public prices are shown for 8 of them. Its official list price is $0.287 per 1M input tokens and $0.861 per 1M output tokens. The lowest paid channel is Hugging Face at $0.06 / $0.20 per 1M, about 13× below the list price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 6.7 on the Intelligence Index. Against its lowest blended price of $0.095 per 1M, that is roughly 71 index points per dollar, which is the value ratio the leaderboards rank on.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 32,000 to 131,072, so the usable window depends on the provider you pick. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-06-30.

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba (China)
$0.29 / $0.86
Blended $0.43 · Cache read —
Lowest paid·Hugging FaceCloud
$0.06 / $0.20
Blended $0.095 · 13.2× spread
1 more $0 channels
Context
131,072
Output limit
8,192
Knowledge cutoff
2024-06-30
Released / updated
2024-11-12 / 2024-11-12
Capabilities
Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence6.7
Value71
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 6.7 ÷ min blended $0.095 = 71

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 9 providers8 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaCloudFree——128,000 ⚠4,096deprecated
Hugging Face
Qwen/Qwen2.5-Coder-32B-Instruct
Cloud$0.06$0.20——131,0728,192
NanoGPTGateway$0.20$0.20$0.10—32,000 ⚠8,192
Alibaba (China)Official
qwen2-5-coder-32b-instruct
First-party$0.29$0.86——131,0728,192
Cloudflare Workers AICloud$0.66$1.00——32,768 ⚠32,768
Kilo Gateway
qwen/qwen-2.5-coder-32b-instruct
Gateway$0.66$1.00——32,768 ⚠29,491
OpenRouter
qwen/qwen-2.5-coder-32b-instruct
Gateway$0.66$1.00——32,768 ⚠29,491
Eden AIGateway$0.66$1.00——32,768 ⚠8,192
Abacus
qwen-2.5-coder-32b
Gateway$0.79$0.79——128,000 ⚠8,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Hugging Face$22.00
2NanoGPT$38.11
3Alibaba (China) · Official$100.45
4Cloudflare Workers AI$182.00
5Kilo Gateway$182.00
6OpenRouter$182.00

1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Hugging Face to save $78.45/mo (78%)

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.86$02026-08-052026-08-142026-08-05 · Input list $0.292026-08-06 · Input list $0.292026-08-07 · Input list $0.292026-08-08 · Input list $0.292026-08-09 · Input list $0.292026-08-10 · Input list $0.292026-08-11 · Input list $0.292026-08-12 · Input list $0.292026-08-13 · Input list $0.292026-08-14 · Input list $0.292026-08-05 · Output list $0.862026-08-06 · Output list $0.862026-08-07 · Output list $0.862026-08-08 · Output list $0.862026-08-09 · Output list $0.862026-08-10 · Output list $0.862026-08-11 · Output list $0.862026-08-12 · Output list $0.862026-08-13 · Output list $0.862026-08-14 · Output list $0.862026-08-05 · Min blended $0.432026-08-06 · Min blended $0.432026-08-07 · Min blended $0.432026-08-08 · Min blended $0.432026-08-09 · Min blended $0.432026-08-10 · Min blended $0.432026-08-11 · Min blended $0.432026-08-12 · Min blended $0.432026-08-13 · Min blended $0.432026-08-14 · Min blended $0.095

Artificial Analysis evaluations6 items

GPQA Diamond41.7%
Humanity's Last Exam3.5%
MMLU-Pro63.5%
LiveCodeBench29.5%
AIME12.0%
MATH-50076.7%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Qwen-Image-2.1same series$0 / $0Qwen 3.8 27B Hemingwaysame series$0.25 / $1.50Qwen 3.8 27B Cybersecuritysame series$0.10 / $0.60Gemma 3 4B ITcheaper alternative$0.20 / $0.20Mistral Nemocheaper alternative$0.15 / $0.15Ministral 3Bcheaper alternative$0.04 / $0.04Command R7Bcheaper alternative$0.038 / $0.15
Data partly from models.dev (MIT) · Alibaba (China) official docs ↗