From abaeb255b2f6615ab72acef8a4519682f462178b Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Fri, 6 Nov 2026 22:35:58 +0000 Subject: [PATCH] gateway: make tinfoil/nomic-embed-text member-facing; add greenpt/green-embeddings; fix nomic price to $0.016/1M MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Remove the team_id scoping on tinfoil/nomic-embed-text: member keys can now call the TEE-protected embedding the co-op's own docs-RAG runs on (co-op traffic unaffected). - Correct nomic's declared price to Tinfoil's published rate ($0.016/1M in, was declared $0.05) and declare its 8K context. - Add greenpt/green-embeddings ($0.20/1M, 2560-dim, 32K ctx) — the only genuinely distinct other embedding model in GreenPT's catalog; their green-embedding slug is the same model (identical vectors verified live). - 15 models served; docs models.md updated in the co-op/docs repo. --- config.yaml | 53 ++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 40 insertions(+), 13 deletions(-) diff --git a/config.yaml b/config.yaml index 2643432..b2f8170 100644 --- a/config.yaml +++ b/config.yaml @@ -11,6 +11,8 @@ # tinfoil/gpt-oss-120b: $0.15 in / $0.60 out per 1M # tinfoil/glm-5.3: $1.80 in / $5.75 out / $0.45 cached per 1M # greenpt/qwen3-embedding-8b: $0.25 in / $0 out per 1M (embeddings, 32K ctx) +# greenpt/green-embeddings: $0.20 in / $0 out per 1M (embeddings, 32K ctx) +# tinfoil/nomic-embed-text: $0.016 in / $0 out per 1M (embeddings, 8K ctx, TEE) # tinfoil/voxtral-small-24b: $0.20 in / $0.60 out per 1M (token-priced audio; # +$0.00008/request on /v1/audio/transcriptions) # Without these, LiteLLM can't price these custom models, so spend shows $0.00 @@ -218,13 +220,17 @@ model_list: input_cost_per_character: 0 input_cost_per_request: 0.002 - # --- Embedding model (Tinfoil, in-TEE) --- + # --- Embedding models (Tinfoil, in-TEE; and GreenPT) --- # nomic-embed-text — 768-dim text embeddings for RAG/semantic search. - # NOT a chat model: it powers /v1/embeddings only. Scoped to the admin - # account's team (model_info.team_id) so member keys cannot call it — it is - # an operator resource for the co-op's own docs-RAG, not a member-facing - # model. The portal also filters it out of the chat-facing /v1/models list by - # its `mode: embedding`. Pricing per Tinfoil catalog: $0.05/1M input, $0 out. + # NOT a chat model: it powers /v1/embeddings only. MEMBER-FACING since + # 2026-11-06 — the team_id scoping (operator-account-only) was removed so + # members get a TEE-protected embedding option. This is the same model the + # co-op's own docs-RAG runs on inside the TEE (Open WebUI's knowledge base); + # that traffic is unaffected by members also being able to call it. The + # portal filters `mode: embedding` out of the chat-facing /v1/models list, so + # it stays API-only. Pricing per Tinfoil catalog (inference.tinfoil.sh + # /v1/models): $0.016/1M input, $0 out — corrected 2026-11-06 from a stale + # $0.05 declaration; 8K context declared so clients don't invent larger. - model_name: tinfoil/nomic-embed-text litellm_params: model: openai/nomic-embed-text @@ -232,17 +238,17 @@ model_list: api_key: os.environ/TINFOIL_API_KEY model_info: mode: embedding - team_id: cdfdf422-633f-4432-8893-cffee82a8325 - input_cost_per_token: 0.00000005 + max_input_tokens: 8192 + input_cost_per_token: 0.000000016 output_cost_per_token: 0.0 # --- Embedding model (GreenPT, member-facing) --- # qwen3-embedding-8b — text embeddings via /v1/embeddings, callable by any - # member key (NOT team-scoped, unlike nomic above). Added 2026-11-06 after a - # member asked for an embedding model: the private (Tinfoil) embedding is an - # operator-only docs-RAG resource, so this fills the member-facing gap on - # renewable EU hosting. The portal filters mode:embedding out of the chat - # picker, so it is API-only — same shape as the audio models above. + # member key. Added 2026-11-06 after a member asked for an embedding model, + # filling the member-facing gap on renewable EU hosting (Tinfoil's private + # embedding was opened to members the same day). The portal filters + # mode:embedding out of the chat picker, so it is API-only — same shape as + # the audio models above. # Pricing per GreenPT /v1/pricing: $0.25/1M input, no output charge # (embeddings return vectors; GreenPT lists maxOutputTokens null), 32K # context. max_input_tokens declared from the provider's contextWindowTokens @@ -258,6 +264,27 @@ model_list: output_cost_per_token: 0.0 max_input_tokens: 32000 + # --- Embedding model (GreenPT, member-facing) --- + # green-embeddings — GreenPT's own embedding model (2560-dim, measured live). + # Added 2026-11-06 after a catalog survey: the only genuinely distinct + # embedding model on GreenPT besides qwen3-embedding-8b. Their catalog also + # lists a `green-embedding` (singular) slug — verified the SAME model + # (identical vectors on the same input), so only green-embeddings is served. + # Cheaper per token than qwen3-embedding-8b; the reranker sibling + # (green-rerank) is a different capability and is NOT served. + # Same shape: /v1/embeddings only, filtered out of the chat picker. + # Pricing per GreenPT /v1/pricing: $0.20/1M input, no output charge, 32K ctx. + - model_name: greenpt/green-embeddings + litellm_params: + model: openai/green-embeddings + api_base: https://api.greenpt.ai/v1 + api_key: os.environ/GREENPT_API_KEY + model_info: + mode: embedding + input_cost_per_token: 0.0000002 + output_cost_per_token: 0.0 + max_input_tokens: 32000 + # Fallback: if DeepSeek is down, use GPT-OSS # NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run # longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek