Qwen3-Coder 480B-A35B Instruct

hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.87Blended $/1M (3:1)

$0.445Input $/1M

$2.145Output $/1M

$2.591M in + 1M out

—Cache read $/1M

#3005 of 5,000Cheapest rank

Provider: Charm Hyper (hyper)
Context: 106,000 tokens
Max output: 10,600 tokens
Capabilities: toolstext

Same model, other providers

“Qwen3-Coder 480B-A35B Instruct” is offered by 5 providers — cheapest-effective first. Abacus is the cheapest at $0.52 blended.

Provider	Input	Output	Blended	Context
Abacus	$0.29	$1.2	$0.52	262k
LLM Gateway	$0.3	$1.3	$0.55	262k
Charm Hyper (this)	$0.445	$2.145	$0.87	106k
Alibaba (China)	$0.861	$3.441	$1.51	262k
Alibaba	$1.5	$7.5	$3.00	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Charm Hyper and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3-coder-480b-a35b-instruct-int4-mixed-ar","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):