From 6f9a1a526f3c03a7dbccac240cf38e15874b611b Mon Sep 17 00:00:00 2001 From: Harsh Bhati Date: Fri, 23 Oct 2026 13:04:38 -0400 Subject: [PATCH 1/3] docs(platform): link the BYOK page to the full model evaluation --- docs/platform/features/byok.mdx | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/docs/platform/features/byok.mdx b/docs/platform/features/byok.mdx index 6a57c6cd8..022499a43 100644 --- a/docs/platform/features/byok.mdx +++ b/docs/platform/features/byok.mdx @@ -124,3 +124,7 @@ Accuracy against cost for every model we tested. The green line marks the best a Scatter chart of accuracy against cost per 1,000 add requests on a log scale, one ring per model, each labelled with its accuracy. Mistral Nemo sits at the far left at $0.68 and 84.1%; Claude Opus 5.5 at the far right at $158.55 and 93.5%. A dashed gray line marks Mem0's default model (free tier) at 92.5%. A green shaded region holds the models above it for under $10 per 1,000 add requests, a gold one the models under $2 per 1,000 add requests, and a dashed green line marks the best accuracy available at each price. Tags mark our picks: best value, DeepSeek V4.1 Flash; best under $1, Amazon Nova Micro; best quality, Claude Opus 5.5. + + + Every model's accuracy, cost and latency, and a calculator for your monthly volume. + From d7f6328206b7e116af7c7d2fdbfca57580a98ee4 Mon Sep 17 00:00:00 2001 From: Harsh Bhati Date: Fri, 23 Oct 2026 13:09:33 -0400 Subject: [PATCH 2/3] docs(platform): link the evaluation in a closing line instead of a card --- docs/platform/features/byok.mdx | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/docs/platform/features/byok.mdx b/docs/platform/features/byok.mdx index 022499a43..7b26c46ea 100644 --- a/docs/platform/features/byok.mdx +++ b/docs/platform/features/byok.mdx @@ -125,6 +125,4 @@ Accuracy against cost for every model we tested. The green line marks the best a Scatter chart of accuracy against cost per 1,000 add requests on a log scale, one ring per model, each labelled with its accuracy. Mistral Nemo sits at the far left at $0.68 and 84.1%; Claude Opus 5.5 at the far right at $158.55 and 93.5%. A dashed gray line marks Mem0's default model (free tier) at 92.5%. A green shaded region holds the models above it for under $10 per 1,000 add requests, a gold one the models under $2 per 1,000 add requests, and a dashed green line marks the best accuracy available at each price. Tags mark our picks: best value, DeepSeek V4.1 Flash; best under $1, Amazon Nova Micro; best quality, Claude Opus 5.5. - - Every model's accuracy, cost and latency, and a calculator for your monthly volume. - +You can see every model's accuracy, cost and latency, and a calculator for your monthly volume, in the [full evaluation](https://mem0.ai/blog/bring-your-own-key-accuracy-cost-latency-by-model). From a34ebb0f69fe1f8687c9dc5bc92bc43b1183f449 Mon Sep 17 00:00:00 2001 From: Harsh Bhati Date: Fri, 23 Oct 2026 13:10:43 -0400 Subject: [PATCH 3/3] docs(platform): match the evaluation line to the page's wording --- docs/platform/features/byok.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/platform/features/byok.mdx b/docs/platform/features/byok.mdx index 7b26c46ea..f2514c7bc 100644 --- a/docs/platform/features/byok.mdx +++ b/docs/platform/features/byok.mdx @@ -125,4 +125,4 @@ Accuracy against cost for every model we tested. The green line marks the best a Scatter chart of accuracy against cost per 1,000 add requests on a log scale, one ring per model, each labelled with its accuracy. Mistral Nemo sits at the far left at $0.68 and 84.1%; Claude Opus 5.5 at the far right at $158.55 and 93.5%. A dashed gray line marks Mem0's default model (free tier) at 92.5%. A green shaded region holds the models above it for under $10 per 1,000 add requests, a gold one the models under $2 per 1,000 add requests, and a dashed green line marks the best accuracy available at each price. Tags mark our picks: best value, DeepSeek V4.1 Flash; best under $1, Amazon Nova Micro; best quality, Claude Opus 5.5. -You can see every model's accuracy, cost and latency, and a calculator for your monthly volume, in the [full evaluation](https://mem0.ai/blog/bring-your-own-key-accuracy-cost-latency-by-model). +The [full evaluation](https://mem0.ai/blog/bring-your-own-key-accuracy-cost-latency-by-model) has the accuracy, cost and latency of every model we tested, and a calculator for your monthly volume.