Context
262K
Max output
262K
Serving providers
3
Cheapest input
$0.13 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
74 t/s
tokens / second
Time to first token
2.67s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 5% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 560.3 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 1214.4 | default | — | |||||||||||||
| GPQA Diamond | 90% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 33% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 63% | default | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 75% | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -18.5 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.3 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.3 | default | — | |||||||||||||
| ||||||||||||||||
| SciCode | 48% | default | — | |||||||||||||
| ||||||||||||||||
| SWE-bench Pro | 58% | default | — | |||||||||||||
| SWE-bench Verified | 78% | default | — | |||||||||||||
| TerminalBench Hard | 34% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 64% | default | — | |||||||||||||
| τ-bench Banking | 23% | default | — | |||||||||||||
| τ²-bench | 93% | default | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.13 to $0.14 per 1M tokens across 3 providers, so the dearest route costs 6% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterCheapest | $0.13 | $0.53 | 1 | |||||||||||||
| ||||||||||||||||
| Novita | $0.14 | $0.58 | 1 | |||||||||||||
| ||||||||||||||||
| DeepInfra | $0.14 | $0.58 | 1 | |||||||||||||
| ||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 34% since first tracked
Cost calculator
estimate your monthly spend on this model$69
estimated / month
Model IDs
copy the exact identifier for your platformtencent/hy3novita/tencent/hy3deepinfra/tencent/Hy3
Frequently asked questions
Hy3 pricing, context and availabilityHow much does Hy3 cost?
Hy3 costs $0.13 per 1M input tokens and $0.53 per 1M output tokens at its cheapest provider via OpenRouter. Across 3 serving providers, input prices range from $0.13 to $0.14 per 1M tokens.
What is the context window of Hy3?
Hy3 accepts up to 262K tokens of context and can return up to 262K output tokens.
Which providers serve Hy3?
Hy3 is available from 3 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest.
What can Hy3 do?
Hy3 supports tool use, reasoning, prompt caching and structured output.
Other Other models
compare pricing across the Other lineup Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI