Skip to content
OhMyGPT

Search

Search pages, models and actions, or paste a request ID…

Qwen3 Coder 480B A35B Instruct

Qwen3 Coder 480B A35B model for large-scale coding and agentic software engineering tasks.

Try in ChatCompare
Input price
$0.495
Output price
$1.98
Context
131K
Max output
66K
1356
—
Released
2025-10-01
InputTextOutputText

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

Pricing

All prices for this model, by service tier.

ItemStandardStandard DiscountPriorityPriority DiscountFlexFlex Discount
Inputper 1M tokens$0.495$0.866252$0.2475
Outputper 1M tokens$1.98$3.465$0.99
Cache readper 1M tokens$0.495$0.866252$0.2475
Estimated cost of common use (500 output tokens each)
One chat message3K input tokens$0.00248$0.00434$0.00124
Agent first turn100K tokens of context, none cached$0.0505$0.0884$0.0252
Each later agent turncontext read from cache, plus 2K new tokens$0.0515$0.0901$0.0257
20-turn agent taskfirst turn plus 19 more$1.03$1.80$0.514

Try it

Runs on your balance and is billed like any API request.

Try one

Later turns reuse the provider’s prompt cache, which can lower cost and latency.

The answer streams in here.

Billed by usage

Similar models

Other models with the same output types at a similar price.

  • Best value (high capability, low cost)
  • Pareto frontier (best available trade-off)
  • Similar models

Capability scores come from independent benchmarks: Epoch AI's ECI index aggregates dozens of public evaluations on a scale anchored at GPT-5 = 150 for direct comparison (CC BY 4.0, as of 2026-11-21). epoch.ai/eci

Prices show our live input rates (USD per million tokens), taking the lowest rate across providers. Dated snapshots and resold variants of the same model are merged into one point; free models are excluded.

How to read this chart: The shaded region marks the sweet spot—models outperforming the median on capability while costing less than the median price. The dashed line (Pareto frontier) connects today's optimal choices: no model beats any point on the line on both price and performance.

Qwen3 Coder 480B A35B InstructThis model
—
Input
$0.495
Output
$1.98
—
Input
$0.4818
Output
$0.9636
149
Input
$0.4592–$0.66
Output
$2.4088–$3.30
152
Input
$0.45–$0.55
Output
$2.70–$3.30
—
Input
$0.55
Output
$1.32

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text