From aa1531bb181c1db409361caf4bdb55357f48ca4d Mon Sep 17 00:00:00 2001 From: Inferencebot Date: Fri, 13 Nov 2026 15:23:47 +0000 Subject: [PATCH] gateway: add Regolo Mistral-Small-4-119B and Gemma-4-31B Operator-approved 2026-11-13. Rates and context read live from Regolo's own model catalog (regolo.ai/models): mistral-small-4-119b $0.20 in / $0.70 out per 1M, 60K in / 60K out; gemma4-31b $0.40 in / $0.60 out, 100K in / 100K out. Routing: same Regolo api_base + REGOLO_API_KEY as the existing regolo entries. models.md member-facing mirror updated in the docs repo separately. --- config.yaml | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/config.yaml b/config.yaml index 9341e3c..127004a 100644 --- a/config.yaml +++ b/config.yaml @@ -13,6 +13,8 @@ # 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) +# regolo/mistral-small-4-119b: $0.20 in / $0.70 out per 1M (60K ctx) +# regolo/gemma4-31b: $0.40 in / $0.60 out per 1M (100K ctx) # 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 @@ -117,6 +119,10 @@ model_list: # qwen3.5-122b: large vision+reasoning MoE (262K ctx). REQUIRES # chat_template_kwargs: {enable_thinking: false} — otherwise the reasoning # phase consumes the entire token budget and content comes back empty. + # mistral-small-4-119b + gemma4-31b: added 2026-11-13 (operator-approved). + # Rates read live from Regolo's own model catalog (regolo.ai/models): + # mistral $0.20/$0.70 per 1M, 60K in / 60K out; gemma4 $0.40/$0.60, + # 100K in / 100K out. # Qwen-Image: image generation via /v1/images/generations, billed per pixel. - model_name: regolo/apertus-70b litellm_params: @@ -139,6 +145,30 @@ model_list: input_cost_per_token: 6.96e-7 output_cost_per_token: 3.944e-6 + # Mistral Small 4 (119B) — hybrid instruct + reasoning model (three model + # families unified by Regolo). $0.20 in / $0.70 out per 1M, 60K ctx. + - model_name: regolo/mistral-small-4-119b + litellm_params: + model: openai/mistral-small-4-119b + api_base: https://api.regolo.ai/v1 + api_key: os.environ/REGOLO_API_KEY + model_info: + mode: chat + input_cost_per_token: 2.0e-7 + output_cost_per_token: 7.0e-7 + + # Gemma 4 (31B) — Google's dense multimodal Gemma 4. $0.40 in / $0.60 out + # per 1M, 100K ctx. + - model_name: regolo/gemma4-31b + litellm_params: + model: openai/gemma4-31b + api_base: https://api.regolo.ai/v1 + api_key: os.environ/REGOLO_API_KEY + model_info: + mode: chat + input_cost_per_token: 4.0e-7 + output_cost_per_token: 6.0e-7 + - model_name: regolo/qwen-image litellm_params: model: openai/Qwen-Image