LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3-Coder 480B-A35B Instruct

alibaba·alibaba/qwen3-coder-480b-a35b-instruct·Deprecated·Open weights·qwen series
Open Qwen coding heavyweight for repository reasoning and agentic engineering

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$1.50 / $7.50
Blended $3.00 · Cache read —
Lowest paid·NanoGPTGateway
$0.13 / $0.50
Blended $0.22 · 15.4× spread
Context
262,144
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2025-07-22 / 2025-07-22
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

Qwen3-Coder 480B-A35B Instruct by alibaba is offered by 25 providers on this page. Its official list price is $1.50 per 1M input tokens and $7.50 per 1M output tokens. The lowest paid channel is NanoGPT at $0.13 / $0.50 per 1M, about 13× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 99 tokens per second, with 1.19s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 106,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. 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 2025-04.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed99 tok/s
TTFT1.19 s

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

Available at 25 providers25 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    qwen/qwen3-coder
    $0.13 / $0.50
    Cache read $0.065Context 262,000 ⚠Output limit 65,536
  • Obscurify.aiGateway
    qwen/qwen3-coder
    $0.14 / $0.55
    Context 262,000 ⚠Output limit 65,536
  • submodelGateway
    Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
    $0.20 / $0.80
    Context 262,144Output limit 262,144
  • HeliconeGateway
    qwen3-coder
    $0.22 / $0.95
    Context 262,144Output limit 16,384
  • SiliconFlowCloud
    Qwen/Qwen3-Coder-480B-A35B-Instruct
    $0.25 / $1.00
    Context 262,000 ⚠Output limit 262,000
  • OpenRouterGateway
    qwen/qwen3-coder
    $0.30 / $1.00
    Cache read $0.10Context 262,144Output limit 65,536
  • Kilo GatewayGateway
    qwen/qwen3-coder
    $0.30 / $1.00
    Cache read $0.10Context 262,144Output limit 65,536
  • Deep InfraCloud
    Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
    $0.30 / $1.00
    Cache read $0.10Context 262,144Output limit 66,536
  • Phase RouterGateway
    qwen3-coder-480b
    $0.31 / $1.04
    Context 262,144Output limit 65,536
  • RuncrateGateway
    Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
    $0.32 / $1.05
    Cache read $0.11Context 262,144Output limit 65,536
  • Alibaba (China)OfficialFirst-party
    $0.86 / $3.44
    tiered >32K: $1.29 · >128K: $2.15
    Context 262,144Output limit 65,536deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
qwen/qwen3-coder
Gateway$0.13$0.50$0.065—262,000 ⚠65,536
Obscurify.ai
qwen/qwen3-coder
Gateway$0.14$0.55——262,000 ⚠65,536
submodel
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
Gateway$0.20$0.80——262,144262,144
Helicone
qwen3-coder
Gateway$0.22$0.95——262,14416,384
SiliconFlow
Qwen/Qwen3-Coder-480B-A35B-Instruct
Cloud$0.25$1.00——262,000 ⚠262,000
OpenRouter
qwen/qwen3-coder
Gateway$0.30$1.00$0.10—262,14465,536
Kilo Gateway
qwen/qwen3-coder
Gateway$0.30$1.00$0.10—262,14465,536
Deep Infra
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
Cloud$0.30$1.00$0.10—262,14466,536
Phase Router
qwen3-coder-480b
Gateway$0.31$1.04——262,14465,536
Runcrate
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
Gateway$0.32$1.05$0.11—262,14465,536
Alibaba (China)OfficialFirst-party$0.86
tiered >32K: $1.29 · >128K: $2.15
$3.44——262,14465,536deprecated

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

Common scenarios
1NanoGPT$43.20
2Obscurify.ai$56.36
3submodel$80.00
4OpenRouter$86.00
5Kilo Gateway$86.00
6Deep Infra$86.00
20Alibaba (China) · Official$344.25
Switch to NanoGPT to save $301.05/mo (87%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$7.50$02026-08-052026-10-21
2026-10-21Input list $1.50Output list $7.50Min blended $0.22

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Prodataset: public38.7resolve rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—GPT-4.1 minicheaper alternative$0.40 / $1.60Grok 4.20 (Non-Reasoning)cheaper alternative$1.25 / $2.50Mistral Large 3cheaper alternative$0.50 / $1.50Codestral 25.08cheaper alternative$0.30 / $0.90Qwen3-Coder 30B-A3B Instructsame lab$0.45 / $2.25Qwen3 Coder Flashsame lab$0.30 / $1.50
Data partly from models.dev (MIT) · Alibaba official docs ↗