Models

qwen3-coder-480b-a35b-instruct

novita · 262K ctx · 6 providers · updated 2026-09-19 02:15 UTC

Cheapest
$0.672 Official list · Novita
Avg price
$0.845 /1M
providers
6
(3 × $0.380 + $1.55) ÷ 4 = $0.672/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.380, 3:1 $0.673, 1:1 $0.965, output only $1.55 per 1M.

The board shows this model's cheapest measured offer ($0.672/1M); the smaller figure under it is the mean of the 8 offers listed below ($0.845/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
novita Pricebook (LiteLLM) $0.380$1.55 Official list
novita HuggingFace Router $0.380$1.55 738ms 60 API-measured
novita-ai Novita AI $0.380$1.55 API-measured
deepinfra Pricebook (LiteLLM) $0.400$1.60 Official list
requesty Requesty $0.400$1.60 API-measured
fireworks_ai Pricebook (LiteLLM) $0.450$1.80 Official list
wandb Pricebook (LiteLLM) $1.00$1.50 Official list
burncloud burncloud $1.14$2.29 API-measured

Price trend

Cheapest blended price, last 31 days (USD/1M): $0.55 → $0.55 → $0.55 → $0.55 → $0.55 → $0.55 → $0.55 → $0.55 → $0.55 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725 → $0.6725

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/qwen3-coder-480b-a35b-instruct.json. Free reuse requires attribution to tkx.org.

FAQ

How much does qwen3-coder-480b-a35b-instruct cost?

Cheapest measured offer right now: $0.38/1M input, $1.55/1M output via novita — across 6 tracked providers, refreshed hourly.

Who serves qwen3-coder-480b-a35b-instruct?

6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of qwen3-coder-480b-a35b-instruct going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings