Hy3 API pricing

7 providers serve Hy3. Hy3 is a proprietary API model, up to 262K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-11-22 · list prices from provider APIs
Input floor $0.140/1M at Novita AI, DeepInfra, Opencode Go and 2 more Output floor $0.580/1M at Novita AI, DeepInfra, Opencode Go and 2 more Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Novita AI $0.140 $0.580output floor $0.035 262K Use
DeepInfra $0.140 $0.580 $0.035 262K Use
Opencode Go $0.140 $0.580 $0.035 192K
GMI Cloud $0.140 $0.580 $0.035 262K Use
OpenRouter marketplace quote $0.140 $0.580 $0.035 262K Use
Aihubmix $0.156 $0.625 $0.039 256K
Kyma $0.159 $0.658 - 262K

The cheapest way to run Hy3

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $27.20/month — the same at Novita AI, DeepInfra, Opencode Go and 2 more. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

FAQ

What is the cheapest API for Hy3?

As of 2026-11-22, the lowest input price for Hy3, $0.140 per 1M tokens, is the same list price at Novita AI, DeepInfra, Opencode Go and 2 more. The lowest output price, $0.580 per 1M tokens, is likewise shared by the same providers. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Aihubmix at $0.156, a 12% difference.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON