Skip to main content

Qwen3 Coder 480B A35B

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

Input / output price
$0.30 / $1.00 per 1M
Context
262K tokens
Released
Jul 22, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen3-coder".

Read docs

Providers

4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/qwen3-coder-480b-a35b
$0.30/M$1.00/M
IO.netionet/qwen3-coder
$0.325/M$1.25/M
Bedrockbedrock/qwen3-coder
$0.45/M$1.80/M
OpenRouteropenrouter/qwen3-coder
$0.30/M$1.00/M

Is a provider down? AWS Bedrock status, OpenRouter status

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.34 per 1M
Average output
$1.26 per 1M
Average cache read
$0.12 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.45/MBedrockLowest$0.30/MConcentrate and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

21tokens/sacross providers

Faster than 39% of the other 599 models on the gateway

Response latency

Lower is better

0.8sacross providers

Faster than 74% of the other 780 models on the gateway

Benchmarks

4 published scores from 3 sources, each linked to where it was published.

Published scores

BenchmarkScore
SWE-bench Verifiedlinkedin.com69.6%
WeirdMLHåvard Tveit Ihle41.2%

Apps

Use Qwen3 Coder 480B A35B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Qwen3 Coder 480B A35B FAQ

Short answers, built from the data on this page.

Qwen3 Coder 480B A35B is a model from Qwen, released on Jul 22, 2025. Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

On the Respan gateway, Qwen3 Coder 480B A35B costs from $0.30 per 1M input tokens and $1.00 per 1M output tokens on Concentrate and OpenRouter, after gateway discounts. Averaged across its 4 providers, it costs $0.34 per 1M input tokens and $1.26 per 1M output tokens.

Qwen3 Coder 480B A35B is available through 4 providers: Concentrate, IO.net, Bedrock, and OpenRouter.

Qwen3 Coder 480B A35B accepts up to 262K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-coder". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen3 Coder 480B A35B has 4 published benchmark scores, including SWE-bench Verified 69.6% and LMArena Elo 1387. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.