Output tokens cost $0.55 per million on gpt-oss-20b and $15.00 per million on Kimi K3. Input tokens cost $0.11 per million on gpt-oss-20b and $3.00 per million on Kimi K3. Cached input tokens are billed at $0.11 per million on gpt-oss-20b and $0.30 per million on Kimi K3. Context lengths are 128,000 tokens on gpt-oss-20b and 1,048,576 tokens on Kimi K3. Time to first token (TTFT) measured on AIHubMix is 0.1s on gpt-oss-20b and 0.9s on Kimi K3. Measured output throughput is 2619.0 tok/s on gpt-oss-20b and 73.1 tok/s on Kimi K3. On the LMArena coding leaderboard gpt-oss-20b scores 1370 and Kimi K3 scores 1531.
gpt-oss-20b
Kimi K3gpt-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.
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
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; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 1531; 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 Kimi K3 accepts 1,048,576 input tokens. Maximum output per request is 128,000 tokens on gpt-oss-20b and 1,048,576 tokens on Kimi K3.
gpt-oss-20b at 2619.0 tok/s and Kimi K3 at 73.1 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; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
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