Output tokens cost $0.55 per million on gpt-oss-20b and $6.00 per million on Grok 4.5. Input tokens cost $0.11 per million on gpt-oss-20b and $2.00 per million on Grok 4.5. Cached input tokens are billed at $0.11 per million on gpt-oss-20b and $0.50 per million on Grok 4.5. Context lengths are 128,000 tokens on gpt-oss-20b and 500,000 tokens on Grok 4.5. Time to first token (TTFT) measured on AIHubMix is 0.1s on gpt-oss-20b and 2.2s on Grok 4.5. Measured output throughput is 2619.0 tok/s on gpt-oss-20b and 28.5 tok/s on Grok 4.5. On the LMArena coding leaderboard gpt-oss-20b scores 1370 and Grok 4.5 scores 1523.
gpt-oss-20b
Grok 4.5gpt-oss-20b is a 21-billion parameter open-weight model released by OpenAI under the Apache 2.0 license. Its core feature is a Mixture-of-Experts (MoE) architecture that uses only 3.6B active parameters, enabling low-latency inference and deployment on consumer GPUs. The model also supports fine-tuning, function calling, tool use, and structured outputs.
Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and math. With both intelligent and efficient reasoning, Grok 4.5 excels at real engineering tasks and exceeds comparable leading models at these tasks.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
gpt-oss-20b: $0.55/M output tokens; Grok 4.5: $6.00/M. Use the cost calculator above to estimate your own workload.
Grok 4.5: 1523; gpt-oss-20b: 1370 (LMArena coding leaderboard).
gpt-oss-20b: 0.1s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
gpt-oss-20b accepts 128,000 and Grok 4.5 accepts 500,000 input tokens. Maximum output per request is 128,000 tokens on gpt-oss-20b and 500,000 tokens on Grok 4.5.
gpt-oss-20b at 2619.0 tok/s and Grok 4.5 at 28.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
gpt-oss-20b accepts text input and supports thinking, function calling and structured outputs; Grok 4.5 accepts text and image input and supports thinking, tool calling, function calling, structured outputs and long context.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix