What is the model comparison matrix?
231 pairwise comparisons across the o10 model catalog with gateway pricing and routing guidance.
o10 State of Inference Spend 2026: up to 638× compliant spread between default and cheapest eval-passing routes.
o10
Model comparison matrix
Pairwise inference cost comparisons. Route to whichever clears your eval floor at lower cost.
Compare model specifications and reference prices, then evaluate candidate models on the same tasks before choosing a route.
Compare231 pairs
claude 3 5 haiku vs claude 3 5 sonnet inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs claude 3 5 sonnet (sonnet, ~$9.4/1M). o10 ro…
claude 3 5 haiku vs claude 3 7 sonnet inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs claude 3 7 sonnet (sonnet, ~$9.8/1M). o10 ro…
claude 3 5 haiku vs claude 3 opus inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs claude 3 opus (frontier, ~$31.9/1M). o10 rou…
claude 3 5 haiku vs codestral inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs codestral (sonnet, ~$0.9/1M). o10 routes to …
claude 3 5 haiku vs deepseek r1 inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs deepseek r1 (reasoning, ~$2.8/1M). o10 route…
claude 3 5 haiku vs gemini 1 5 flash inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 rout…
claude 3 5 haiku vs gemini 1 5 pro inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 route…
claude 3 5 haiku vs gemini 2 0 flash inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 route…
claude 3 5 haiku vs gpt 4 turbo inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes …
claude 3 5 haiku vs gpt 4.1 inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to …
claude 3 5 haiku vs gpt 4.1 mini inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes t…
claude 3 5 haiku vs gpt 4o inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whi…
claude 3 5 haiku vs gpt 4o mini inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to …
claude 3 5 haiku vs llama 3 1 70b inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 r…
claude 3 5 haiku vs llama 3 1 8b inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 r…
claude 3 5 haiku vs mistral large inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes t…
claude 3 5 haiku vs mistral small inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes t…
claude 3 5 haiku vs mixtral 8x7b inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 ro…
claude 3 5 haiku vs o1 inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to which…
claude 3 5 haiku vs o1 mini inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to w…
claude 3 5 haiku vs titan text inference cost
claude 3 5 haiku (mini, ~$0.65/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to w…
claude 3 5 sonnet vs claude 3 7 sonnet inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs claude 3 7 sonnet (sonnet, ~$9.8/1M). o10 …
claude 3 5 sonnet vs claude 3 opus inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs claude 3 opus (frontier, ~$31.9/1M). o10 r…
claude 3 5 sonnet vs codestral inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs codestral (sonnet, ~$0.9/1M). o10 routes t…
claude 3 5 sonnet vs deepseek r1 inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs deepseek r1 (reasoning, ~$2.8/1M). o10 rou…
claude 3 5 sonnet vs gemini 1 5 flash inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 ro…
claude 3 5 sonnet vs gemini 1 5 pro inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 rou…
claude 3 5 sonnet vs gemini 2 0 flash inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 rou…
claude 3 5 sonnet vs gpt 4 turbo inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 route…
claude 3 5 sonnet vs gpt 4.1 inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes t…
claude 3 5 sonnet vs gpt 4.1 mini inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes…
claude 3 5 sonnet vs gpt 4o inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to w…
claude 3 5 sonnet vs gpt 4o mini inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes t…
claude 3 5 sonnet vs llama 3 1 70b inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10…
claude 3 5 sonnet vs llama 3 1 8b inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10…
claude 3 5 sonnet vs mistral large inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes…
claude 3 5 sonnet vs mistral small inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes…
claude 3 5 sonnet vs mixtral 8x7b inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 …
claude 3 5 sonnet vs o1 inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whi…
claude 3 5 sonnet vs o1 mini inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to…
claude 3 5 sonnet vs titan text inference cost
claude 3 5 sonnet (sonnet, ~$9.4/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to…
claude 3 7 sonnet vs claude 3 opus inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs claude 3 opus (frontier, ~$31.9/1M). o10 r…
claude 3 7 sonnet vs codestral inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs codestral (sonnet, ~$0.9/1M). o10 routes t…
claude 3 7 sonnet vs deepseek r1 inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs deepseek r1 (reasoning, ~$2.8/1M). o10 rou…
claude 3 7 sonnet vs gemini 1 5 flash inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 ro…
claude 3 7 sonnet vs gemini 1 5 pro inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 rou…
claude 3 7 sonnet vs gemini 2 0 flash inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 rou…
claude 3 7 sonnet vs gpt 4 turbo inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 route…
claude 3 7 sonnet vs gpt 4.1 inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes t…
claude 3 7 sonnet vs gpt 4.1 mini inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes…
claude 3 7 sonnet vs gpt 4o inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to w…
claude 3 7 sonnet vs gpt 4o mini inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes t…
claude 3 7 sonnet vs llama 3 1 70b inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10…
claude 3 7 sonnet vs llama 3 1 8b inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10…
claude 3 7 sonnet vs mistral large inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes…
claude 3 7 sonnet vs mistral small inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes…
claude 3 7 sonnet vs mixtral 8x7b inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 …
claude 3 7 sonnet vs o1 inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whi…
claude 3 7 sonnet vs o1 mini inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to…
claude 3 7 sonnet vs titan text inference cost
claude 3 7 sonnet (sonnet, ~$9.8/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to…
claude 3 opus vs codestral inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs codestral (sonnet, ~$0.9/1M). o10 routes to…
claude 3 opus vs deepseek r1 inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs deepseek r1 (reasoning, ~$2.8/1M). o10 rout…
claude 3 opus vs gemini 1 5 flash inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 rou…
claude 3 opus vs gemini 1 5 pro inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 rout…
claude 3 opus vs gemini 2 0 flash inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 rout…
claude 3 opus vs gpt 4 turbo inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes…
claude 3 opus vs gpt 4.1 inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to…
claude 3 opus vs gpt 4.1 mini inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes …
claude 3 opus vs gpt 4o inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to wh…
claude 3 opus vs gpt 4o mini inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to…
claude 3 opus vs llama 3 1 70b inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 …
claude 3 opus vs llama 3 1 8b inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 …
claude 3 opus vs mistral large inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes …
claude 3 opus vs mistral small inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes …
claude 3 opus vs mixtral 8x7b inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 r…
claude 3 opus vs o1 inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whic…
claude 3 opus vs o1 mini inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to …
claude 3 opus vs titan text inference cost
claude 3 opus (frontier, ~$31.9/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to …
codestral vs deepseek r1 inference cost
codestral (sonnet, ~$0.9/1M gateway) vs deepseek r1 (reasoning, ~$2.8/1M). o10 routes to w…
codestral vs gemini 1 5 flash inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 routes to …
codestral vs gemini 1 5 pro inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 routes to w…
codestral vs gemini 2 0 flash inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 routes to w…
codestral vs gpt 4 turbo inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes to whi…
codestral vs gpt 4.1 inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to whiche…
codestral vs gpt 4.1 mini inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to whic…
codestral vs gpt 4o inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whichever…
codestral vs gpt 4o mini inference cost
codestral (sonnet, ~$0.9/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to whiche…
codestral vs llama 3 1 70b inference cost
codestral (sonnet, ~$0.9/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 routes …
codestral vs llama 3 1 8b inference cost
codestral (sonnet, ~$0.9/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 routes …
codestral vs mistral large inference cost
codestral (sonnet, ~$0.9/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to whic…
codestral vs mistral small inference cost
codestral (sonnet, ~$0.9/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to whic…
codestral vs mixtral 8x7b inference cost
codestral (sonnet, ~$0.9/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes t…
codestral vs o1 inference cost
codestral (sonnet, ~$0.9/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever c…
codestral vs o1 mini inference cost
codestral (sonnet, ~$0.9/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whichev…
codestral vs titan text inference cost
codestral (sonnet, ~$0.9/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whichev…
deepseek r1 vs gemini 1 5 flash inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gemini 1 5 flash (mini, ~$0.35/1M). o10 route…
deepseek r1 vs gemini 1 5 pro inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 routes…
deepseek r1 vs gemini 2 0 flash inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 routes…
deepseek r1 vs gpt 4 turbo inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes t…
deepseek r1 vs gpt 4.1 inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to w…
deepseek r1 vs gpt 4.1 mini inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to…
deepseek r1 vs gpt 4o inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whic…
deepseek r1 vs gpt 4o mini inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to w…
deepseek r1 vs llama 3 1 70b inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 ro…
deepseek r1 vs llama 3 1 8b inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 ro…
deepseek r1 vs mistral large inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to…
deepseek r1 vs mistral small inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to…
deepseek r1 vs mixtral 8x7b inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 rou…
deepseek r1 vs o1 inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whiche…
deepseek r1 vs o1 mini inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to wh…
deepseek r1 vs titan text inference cost
deepseek r1 (reasoning, ~$2.8/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to wh…
gemini 1 5 flash vs gemini 1 5 pro inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gemini 1 5 pro (sonnet, ~$3.5/1M). o10 route…
gemini 1 5 flash vs gemini 2 0 flash inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 route…
gemini 1 5 flash vs gpt 4 turbo inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes …
gemini 1 5 flash vs gpt 4.1 inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to …
gemini 1 5 flash vs gpt 4.1 mini inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes t…
gemini 1 5 flash vs gpt 4o inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whi…
gemini 1 5 flash vs gpt 4o mini inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to …
gemini 1 5 flash vs llama 3 1 70b inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 r…
gemini 1 5 flash vs llama 3 1 8b inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 r…
gemini 1 5 flash vs mistral large inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes t…
gemini 1 5 flash vs mistral small inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes t…
gemini 1 5 flash vs mixtral 8x7b inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 ro…
gemini 1 5 flash vs o1 inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to which…
gemini 1 5 flash vs o1 mini inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to w…
gemini 1 5 flash vs titan text inference cost
gemini 1 5 flash (mini, ~$0.35/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to w…
gemini 1 5 pro vs gemini 2 0 flash inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gemini 2 0 flash (mini, ~$0.4/1M). o10 routes…
gemini 1 5 pro vs gpt 4 turbo inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes t…
gemini 1 5 pro vs gpt 4.1 inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to w…
gemini 1 5 pro vs gpt 4.1 mini inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to…
gemini 1 5 pro vs gpt 4o inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whic…
gemini 1 5 pro vs gpt 4o mini inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to w…
gemini 1 5 pro vs llama 3 1 70b inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 ro…
gemini 1 5 pro vs llama 3 1 8b inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 ro…
gemini 1 5 pro vs mistral large inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to…
gemini 1 5 pro vs mistral small inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to…
gemini 1 5 pro vs mixtral 8x7b inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 rou…
gemini 1 5 pro vs o1 inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whiche…
gemini 1 5 pro vs o1 mini inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to wh…
gemini 1 5 pro vs titan text inference cost
gemini 1 5 pro (sonnet, ~$3.5/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to wh…
gemini 2 0 flash vs gpt 4 turbo inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs gpt 4 turbo (frontier, ~$10/1M). o10 routes t…
gemini 2 0 flash vs gpt 4.1 inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to w…
gemini 2 0 flash vs gpt 4.1 mini inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to…
gemini 2 0 flash vs gpt 4o inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whic…
gemini 2 0 flash vs gpt 4o mini inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to w…
gemini 2 0 flash vs llama 3 1 70b inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 ro…
gemini 2 0 flash vs llama 3 1 8b inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 ro…
gemini 2 0 flash vs mistral large inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to…
gemini 2 0 flash vs mistral small inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to…
gemini 2 0 flash vs mixtral 8x7b inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 rou…
gemini 2 0 flash vs o1 inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whiche…
gemini 2 0 flash vs o1 mini inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to wh…
gemini 2 0 flash vs titan text inference cost
gemini 2 0 flash (mini, ~$0.4/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to wh…
gpt 4 turbo vs gpt 4.1 inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs gpt 4.1 (frontier, ~$4.5/1M). o10 routes to whi…
gpt 4 turbo vs gpt 4.1 mini inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to w…
gpt 4 turbo vs gpt 4o inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whiche…
gpt 4 turbo vs gpt 4o mini inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to whi…
gpt 4 turbo vs llama 3 1 70b inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 rout…
gpt 4 turbo vs llama 3 1 8b inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 rout…
gpt 4 turbo vs mistral large inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to w…
gpt 4 turbo vs mistral small inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to w…
gpt 4 turbo vs mixtral 8x7b inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 route…
gpt 4 turbo vs o1 inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whicheve…
gpt 4 turbo vs o1 mini inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whic…
gpt 4 turbo vs titan text inference cost
gpt 4 turbo (frontier, ~$10/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whic…
gpt 4.1 vs gpt 4.1 mini inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs gpt 4.1 mini (mini, ~$0.55/1M). o10 routes to whic…
gpt 4.1 vs gpt 4o inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whichever…
gpt 4.1 vs gpt 4o mini inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to whiche…
gpt 4.1 vs llama 3 1 70b inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 routes …
gpt 4.1 vs llama 3 1 8b inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 routes …
gpt 4.1 vs mistral large inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to whic…
gpt 4.1 vs mistral small inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to whic…
gpt 4.1 vs mixtral 8x7b inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes t…
gpt 4.1 vs o1 inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever c…
gpt 4.1 vs o1 mini inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whichev…
gpt 4.1 vs titan text inference cost
gpt 4.1 (frontier, ~$4.5/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whichev…
gpt 4.1 mini vs gpt 4o inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs gpt 4o (frontier, ~$5/1M). o10 routes to whichev…
gpt 4.1 mini vs gpt 4o mini inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to whic…
gpt 4.1 mini vs llama 3 1 70b inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 route…
gpt 4.1 mini vs llama 3 1 8b inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 route…
gpt 4.1 mini vs mistral large inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to wh…
gpt 4.1 mini vs mistral small inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to wh…
gpt 4.1 mini vs mixtral 8x7b inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes…
gpt 4.1 mini vs o1 inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever…
gpt 4.1 mini vs o1 mini inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to which…
gpt 4.1 mini vs titan text inference cost
gpt 4.1 mini (mini, ~$0.55/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to which…
gpt 4o vs gpt 4o mini inference cost
gpt 4o (frontier, ~$5/1M gateway) vs gpt 4o mini (mini, ~$0.6/1M). o10 routes to whichever…
gpt 4o vs llama 3 1 70b inference cost
gpt 4o (frontier, ~$5/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 routes to …
gpt 4o vs llama 3 1 8b inference cost
gpt 4o (frontier, ~$5/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 routes to …
gpt 4o vs mistral large inference cost
gpt 4o (frontier, ~$5/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to whichev…
gpt 4o vs mistral small inference cost
gpt 4o (frontier, ~$5/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to whichev…
gpt 4o vs mixtral 8x7b inference cost
gpt 4o (frontier, ~$5/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes to w…
gpt 4o vs o1 inference cost
gpt 4o (frontier, ~$5/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever clea…
gpt 4o vs o1 mini inference cost
gpt 4o (frontier, ~$5/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whichever …
gpt 4o vs titan text inference cost
gpt 4o (frontier, ~$5/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whichever …
gpt 4o mini vs llama 3 1 70b inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs llama 3 1 70b (open-weight, ~$0.9/1M). o10 routes …
gpt 4o mini vs llama 3 1 8b inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o10 routes …
gpt 4o mini vs mistral large inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 routes to whic…
gpt 4o mini vs mistral small inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to whic…
gpt 4o mini vs mixtral 8x7b inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes t…
gpt 4o mini vs o1 inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever c…
gpt 4o mini vs o1 mini inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whichev…
gpt 4o mini vs titan text inference cost
gpt 4o mini (mini, ~$0.6/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whichev…
llama 3 1 70b vs llama 3 1 8b inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs llama 3 1 8b (open-weight, ~$0.12/1M). o1…
llama 3 1 70b vs mistral large inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 route…
llama 3 1 70b vs mistral small inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 route…
llama 3 1 70b vs mixtral 8x7b inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10…
llama 3 1 70b vs o1 inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to wh…
llama 3 1 70b vs o1 mini inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes t…
llama 3 1 70b vs titan text inference cost
llama 3 1 70b (open-weight, ~$0.9/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes t…
llama 3 1 8b vs mistral large inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs mistral large (sonnet, ~$3/1M). o10 route…
llama 3 1 8b vs mistral small inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 route…
llama 3 1 8b vs mixtral 8x7b inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10…
llama 3 1 8b vs o1 inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to wh…
llama 3 1 8b vs o1 mini inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes t…
llama 3 1 8b vs titan text inference cost
llama 3 1 8b (open-weight, ~$0.12/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes t…
mistral large vs mistral small inference cost
mistral large (sonnet, ~$3/1M gateway) vs mistral small (mini, ~$0.2/1M). o10 routes to wh…
mistral large vs mixtral 8x7b inference cost
mistral large (sonnet, ~$3/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes…
mistral large vs o1 inference cost
mistral large (sonnet, ~$3/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever…
mistral large vs o1 mini inference cost
mistral large (sonnet, ~$3/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to which…
mistral large vs titan text inference cost
mistral large (sonnet, ~$3/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to which…
mistral small vs mixtral 8x7b inference cost
mistral small (mini, ~$0.2/1M gateway) vs mixtral 8x7b (open-weight, ~$0.6/1M). o10 routes…
mistral small vs o1 inference cost
mistral small (mini, ~$0.2/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whichever…
mistral small vs o1 mini inference cost
mistral small (mini, ~$0.2/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to which…
mistral small vs titan text inference cost
mistral small (mini, ~$0.2/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to which…
mixtral 8x7b vs o1 inference cost
mixtral 8x7b (open-weight, ~$0.6/1M gateway) vs o1 (reasoning, ~$15/1M). o10 routes to whi…
mixtral 8x7b vs o1 mini inference cost
mixtral 8x7b (open-weight, ~$0.6/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to…
mixtral 8x7b vs titan text inference cost
mixtral 8x7b (open-weight, ~$0.6/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to…
o1 vs o1 mini inference cost
o1 (reasoning, ~$15/1M gateway) vs o1 mini (reasoning, ~$3/1M). o10 routes to whichever cl…
o1 vs titan text inference cost
o1 (reasoning, ~$15/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whichever cl…
o1 mini vs titan text inference cost
o1 mini (reasoning, ~$3/1M gateway) vs titan text (mini, ~$0.8/1M). o10 routes to whicheve…
Start hereQuick overview
How to use this index
FAQFrequently asked questions
Common questions
How many model comparisons?
231 unique pairs from the model catalog.
How are pairs ranked?
By gateway pricing and typical eval-floor fit. Always verify in shadow mode on your traffic.
Does o10 replace a gateway?
No. o10 sits above gateways and picks the cheaper compliant tier per use case after eval proof.
o10Set the envelope. o10 holds it.
See what you're overpaying.
Paste a week of traffic. Get the number that books the audit.
See what you're overpaying →