Novita AIlow cost

Qwen3.5-122B-A10B API Pricing

Qwen3.5-122B-A10B costs $0.40 per 1M input tokens and $3.20 per 1M output tokens. These rates were last verified on .

Model quality and API cost

Task scores are separate from token prices. Provider-reported results; no universal quality ranking.

Canonical API costs and attributed task-specific benchmark scores
MetricQwen3.5-122B-A10B
Input · USD / 1M$0.40
Output · USD / 1M$3.20
Cached input · USD / 1MNot listed
Context · tokensNot published
Price source / checkOfficial rates2026-11-16
Quality coverageNo published result found in this pilot — not a zero score.

Prices are canonical recorded API token rates, not benchmark-run costs or subscription charges. Check the model page for overdue verification, context tiers, scheduled rates, tools and thinking-token billing. Context limits can be shared input/output budgets.

Comparability not established: snapshots or evaluation conditions are incomplete. No winner, performance delta or quality-per-dollar score is calculated.

Coverage: 0/1 displayed models. Missing means not found in this bounded pilot, not never tested. Weekly and new-model review is currently manual.

Published rates and billing units

Billing dimensionUSD list price
Input / 1M tokens$0.40
Output / 1M tokens$3.20

Verified 2026-11-16 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.

Cost examples

These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.

1M input + 1M output

$3.60

A direct per-million comparison against every other text model.

100K input + 25K output

$0.12

A compact chat, summarization, or analysis workload.

10M input + 2M output

$10.40

A monthly production estimate for heavier RAG or agent traffic.

75% cached input + 250K output

Not listed

Novita AI does not publish a cached-input rate for this model in our dataset.

Calculator for Qwen3.5-122B-A10B

Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only Qwen3.5-122B-A10B, so the result stays focused on this model.

Input cost

$0.40

Output cost

$3.20

Total

$3.60

Price history

No list-price movement across 117 daily snapshots from 2026-07-22 to 2026-11-15.

When to use Qwen3.5-122B-A10B

Good fit

  • high-volume routing, classification, extraction, summaries, and fallback traffic

Be careful with

  • decisions that depend on unpublished context-window limits without checking the provider docs first

Alternatives to compare