From f65abcd6329fd8e793388eb895bf80971d105987 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo[bot]@users.noreply.github.com> Date: Mon, 3 Aug 2026 21:17:58 +0000 Subject: [PATCH 1/4] docs(models): clarify free BYOK and ChatGPT access Co-authored-by: Cooper <126418690+cooper-gadd@users.noreply.github.com> --- features/model-settings.mdx | 5 +++++ features/models.mdx | 11 +++++++++-- resources/pricing.mdx | 4 ++-- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/features/model-settings.mdx b/features/model-settings.mdx index 5d8a98e..361d051 100644 --- a/features/model-settings.mdx +++ b/features/model-settings.mdx @@ -25,9 +25,14 @@ You can manage model provider credentials in one place: - Amp API key - Cursor API key - AWS Bedrock access key, secret key, and region +- GCP Vertex AI service account JSON, project, and location Keys are saved at the workspace level and used when a selected model requires that provider. +Anthropic, OpenAI, Amp, and Cursor credentials are available on every Tembo plan, including Free. AWS Bedrock and GCP Vertex AI credentials require a paid Tembo plan. + +To use a paid ChatGPT subscription with Codex, OpenCode, or Pi, connect it from **Settings > Connected Accounts**. ChatGPT connections are available on every Tembo plan. + ## Custom MCP servers (global JSON) `globalMcpServers` lets you define shared MCP servers available across tasks and automations. diff --git a/features/models.mdx b/features/models.mdx index 6d13e31..dc8155c 100644 --- a/features/models.mdx +++ b/features/models.mdx @@ -3,18 +3,25 @@ title: "Models" description: "Supported models, providers, and BYOK options." --- -Tembo supports multiple model providers across coding agents. You can use Tembo-hosted models with [Max](/features/max), or connect your own keys with BYOK (Bring Your Own Key). +Tembo supports multiple model providers across coding agents. The Free plan includes select open-source models through Tembo Managed Inference, while paid plans unlock the full managed model catalog. You can also connect your own model access with BYOK (Bring Your Own Key) or a paid ChatGPT subscription. ## BYOK (Bring Your Own Key) BYOK lets your workspace call models with your own provider credentials instead of Tembo-managed credentials. - Add keys in **Settings -> Models -> API Keys**. -- You can connect OpenAI, Anthropic, Cursor, Amp, AWS Bedrock, and GCP Vertex AI credentials. +- You can connect OpenAI, Anthropic, Cursor, and Amp credentials on every Tembo plan, including Free. +- AWS Bedrock and GCP Vertex AI credentials require a paid Tembo plan. - Tembo still handles orchestration, session context, sandbox execution, and PR automation. BYOK inference costs $0 through Tembo. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](/resources/pricing). +## ChatGPT subscriptions + +You can connect a paid ChatGPT subscription in **Settings > Connected Accounts** on every Tembo plan, including Free. The subscription provides access to supported OpenAI models when you use Codex, OpenCode, or Pi. + +ChatGPT/Codex OAuth inference costs $0 through Tembo. Cloud VM compute still draws from your workspace's [usage allowance](/resources/pricing). + ### Switch a model between BYOK and Tembo Managed Inference Workspace admins can change the inference provider for individual models from **Settings -> Models**. diff --git a/resources/pricing.mdx b/resources/pricing.mdx index d0b330c..1c3da85 100644 --- a/resources/pricing.mdx +++ b/resources/pricing.mdx @@ -13,7 +13,7 @@ Tembo gives your workspace a dollar-denominated usage allowance. Tembo Gateway u Pro and Max can use overage billing so your work can continue after you use your monthly allowance and prepaid balance. You can set a maximum overage limit to control spend. On Free, new sessions are blocked when the allowance and prepaid balance are exhausted until you upgrade or add funds. -BYOK (Bring Your Own Key) is available on Pro, Max, and Enterprise. +Anthropic and OpenAI BYOK, Amp and Cursor keys, and paid ChatGPT subscriptions are available on every Tembo plan, including Free. AWS Bedrock and GCP Vertex AI BYOK require Pro, Max, or Enterprise. ## How the usage allowance works @@ -22,7 +22,7 @@ Two usage categories draw from the same balance: - **Tembo Gateway**: model input, output, and cache usage is charged at the rates in [Tembo Gateway pricing](#tembo-gateway-pricing). - **Cloud VM compute**: metered from the CPU, memory, and runtime used by each session. -BYOK and ChatGPT/Codex OAuth inference cost \$0 through Tembo because you provide the model access. The cloud VM running the session continues to draw from your usage allowance. +BYOK and ChatGPT/Codex OAuth inference cost \$0 through Tembo because you provide the model access. ChatGPT access requires a paid ChatGPT subscription. The cloud VM running the session continues to draw from your usage allowance. Included monthly allowance expires at the end of each billing cycle and does not roll over. Prepaid balance does not expire. From 12f81234b2f90911d3be51ba4941f3c2b7ea6dd8 Mon Sep 17 00:00:00 2001 From: "tembo[bot]" <208362400+tembo[bot]@users.noreply.github.com> Date: Mon, 3 Aug 2026 21:24:14 +0000 Subject: [PATCH 2/4] docs(models): fold ChatGPT access into BYOK copy Co-authored-by: Cooper <126418690+cooper-gadd@users.noreply.github.com> --- features/models.mdx | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/features/models.mdx b/features/models.mdx index dc8155c..f0a226b 100644 --- a/features/models.mdx +++ b/features/models.mdx @@ -14,13 +14,7 @@ BYOK lets your workspace call models with your own provider credentials instead - AWS Bedrock and GCP Vertex AI credentials require a paid Tembo plan. - Tembo still handles orchestration, session context, sandbox execution, and PR automation. -BYOK inference costs $0 through Tembo. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](/resources/pricing). - -## ChatGPT subscriptions - -You can connect a paid ChatGPT subscription in **Settings > Connected Accounts** on every Tembo plan, including Free. The subscription provides access to supported OpenAI models when you use Codex, OpenCode, or Pi. - -ChatGPT/Codex OAuth inference costs $0 through Tembo. Cloud VM compute still draws from your workspace's [usage allowance](/resources/pricing). +BYOK inference costs $0 through Tembo. You can also connect a paid ChatGPT subscription on every Tembo plan, including Free, to use supported OpenAI models with Codex, OpenCode, or Pi. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](/resources/pricing). ### Switch a model between BYOK and Tembo Managed Inference From 80ae772b750989ad4e2d65069f48db8278b09f76 Mon Sep 17 00:00:00 2001 From: Cooper Gadd <126418690+cooper-gadd@users.noreply.github.com> Date: Thu, 6 Aug 2026 12:33:17 -0400 Subject: [PATCH 3/4] docs(models): keep free plan update focused --- features/model-settings.mdx | 5 ----- 1 file changed, 5 deletions(-) diff --git a/features/model-settings.mdx b/features/model-settings.mdx index de57a94..f93a572 100644 --- a/features/model-settings.mdx +++ b/features/model-settings.mdx @@ -25,14 +25,9 @@ You can manage model provider credentials in one place: - Amp API key - Cursor API key - AWS Bedrock access key, secret key, and region -- GCP Vertex AI service account JSON, project, and location Keys are saved at the workspace level and used when a selected model requires that provider. -Anthropic, OpenAI, Amp, and Cursor credentials are available on every Tembo plan, including Free. AWS Bedrock and GCP Vertex AI credentials require a paid Tembo plan. - -To use a paid ChatGPT subscription with Codex, OpenCode, or Pi, connect it from **Settings > Connected Accounts**. ChatGPT connections are available on every Tembo plan. - ## Custom MCP servers (global JSON) `globalMcpServers` lets you define shared MCP servers available across sessions and automations. From 9972daf12f2ac7f0a6175ddc5a2295aa1f31fe8a Mon Sep 17 00:00:00 2001 From: Cooper Gadd <126418690+cooper-gadd@users.noreply.github.com> Date: Thu, 6 Aug 2026 14:04:56 -0400 Subject: [PATCH 4/4] docs(models): simplify BYOK and ChatGPT copy --- features/models.mdx | 4 ++-- resources/pricing.mdx | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/features/models.mdx b/features/models.mdx index f0a226b..4cddf7c 100644 --- a/features/models.mdx +++ b/features/models.mdx @@ -3,7 +3,7 @@ title: "Models" description: "Supported models, providers, and BYOK options." --- -Tembo supports multiple model providers across coding agents. The Free plan includes select open-source models through Tembo Managed Inference, while paid plans unlock the full managed model catalog. You can also connect your own model access with BYOK (Bring Your Own Key) or a paid ChatGPT subscription. +Tembo supports multiple model providers across coding agents. The Free plan includes select open-source models through Tembo Managed Inference, while paid plans unlock the full managed model catalog. You can also connect your own model access with BYOK (Bring Your Own Key) or a ChatGPT subscription. ## BYOK (Bring Your Own Key) @@ -14,7 +14,7 @@ BYOK lets your workspace call models with your own provider credentials instead - AWS Bedrock and GCP Vertex AI credentials require a paid Tembo plan. - Tembo still handles orchestration, session context, sandbox execution, and PR automation. -BYOK inference costs $0 through Tembo. You can also connect a paid ChatGPT subscription on every Tembo plan, including Free, to use supported OpenAI models with Codex, OpenCode, or Pi. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](/resources/pricing). +BYOK inference costs $0 through Tembo. You can also connect a ChatGPT subscription on every Tembo plan, including Free, to use supported OpenAI models with Codex, OpenCode, or Pi. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](/resources/pricing). ### Switch a model between BYOK and Tembo Managed Inference diff --git a/resources/pricing.mdx b/resources/pricing.mdx index a51ce32..f5e681a 100644 --- a/resources/pricing.mdx +++ b/resources/pricing.mdx @@ -22,7 +22,7 @@ Two usage categories draw from the same balance: - **Tembo Gateway**: model input, output, and cache usage is charged at the rates in [Tembo Gateway pricing](#tembo-gateway-pricing). - **Cloud VM compute**: metered from the CPU, memory, and runtime used by each session. -BYOK and ChatGPT/Codex OAuth inference cost \$0 through Tembo because you provide the model access. ChatGPT access requires a paid ChatGPT subscription. The cloud VM running the session continues to draw from your usage allowance. +BYOK and ChatGPT/Codex OAuth inference cost \$0 through Tembo because you provide the model access. The cloud VM running the session continues to draw from your usage allowance. Included monthly allowance expires at the end of each billing cycle and does not roll over. Prepaid balance does not expire.