[BOT ISSUE] Missing Gemini image generation and embedding models with published pricing

[github-actions]

Gap

Several Google Gemini models with published pricing on the official Google AI pricing page are missing from the Braintrust proxy model catalog. The catalog already includes gemini-3-pro-image-preview (line ~5942 in model_list.json), confirming that image generation models are in scope.

Missing image generation models

Model ID	Input $/M tokens	Output $/M tokens	Notes
gemini-3.1-flash-image-preview	Published on Google pricing page	Published on Google pricing page	Flash-tier image generation, analogous to existing gemini-3-pro-image-preview
gemini-2.5-flash-image	Published on Google pricing page	Published on Google pricing page	Older generation image model

Missing embedding model

Model ID	Notes
gemini-embedding-2-preview	Google's embedding model with published pricing; the catalog already tracks OpenAI and Fireworks embedding models

Missing specialized model

Model ID	Notes
gemini-2.5-computer-use-preview-10-2025	Computer use model with published pricing

Official source

• https://ai.google.dev/pricing — lists all models above with explicit pricing
• https://ai.google.dev/gemini-api/docs/models — model documentation

Local files inspected

• packages/proxy/schema/model_list.json — grep for gemini-3.1-flash-image, gemini-2.5-flash-image, gemini-embedding-2, gemini-2.5-computer-use returns no matches
• gemini-3-pro-image-preview IS present at line ~5942, confirming image models are in scope

Why high confidence

These models are listed on Google's official pricing page with explicit per-token pricing. The catalog already includes gemini-3-pro-image-preview, establishing precedent that Gemini image generation models belong in the catalog. The embedding model follows the same pattern as OpenAI text-embedding-3-large/small already tracked in the catalog. The Google provider is fully supported.

Out of scope (not included)

TTS, live streaming, and native audio models (gemini-*-tts-*, gemini-*-live-*, gemini-*-native-audio-*) were found on the pricing page but excluded from this issue as they represent a different modality not currently tracked in the catalog.

[github-actions]

Prepared catalog updates for gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025. Added models: gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025.

Verification sources: https://ai.google.dev/pricing, https://ai.google.dev/gemini-api/docs/models, https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview, https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image, https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2-preview, https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025
Verified metadata applied:

• gemini-3.1-flash-image-preview: format=google, flavor=chat, displayName=Gemini 3.1 Flash Image Preview, max_input_tokens=131072, max_output_tokens=32768, pricing(input/output per 1M)=0.5/3, providers=google|vertex, supported_regions=global, multimodal=true
• gemini-2.5-flash-image: format=google, flavor=chat, displayName=Gemini 2.5 Flash Image, max_input_tokens=65536, max_output_tokens=32768, pricing(input/output per 1M)=0.3/?, providers=google|vertex, supported_regions=global|europe-central2|europe-north1|europe-southwest1|europe-west1|europe-west4|europe-west8|us-central1|us-east1|us-east4|us-east5|us-south1|us-west1|us-west4, multimodal=true
• gemini-embedding-2-preview: format=google, flavor=chat, displayName=Gemini Embedding 2 Preview, max_input_tokens=8192, max_output_tokens=not provided, pricing(input/output per 1M)=0.2/?, providers=google, multimodal=true
• gemini-2.5-computer-use-preview-10-2025: format=google, flavor=chat, displayName=Gemini 2.5 Computer Use Preview, max_input_tokens=128000, max_output_tokens=64000, pricing(input/output per 1M)=1.25/10, providers=google, multimodal=true

Opened #472 to apply the catalog update.

[github-actions]

Prepared catalog updates for gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025. Added models: gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025.

Verification sources: https://ai.google.dev/pricing, https://ai.google.dev/gemini-api/docs/models, https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image-preview, https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image, https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2-preview, https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025
Verified metadata applied:

• gemini-3.1-flash-image-preview: format=google, flavor=chat, displayName=Gemini 3.1 Flash Image Preview, max_input_tokens=131072, max_output_tokens=32768, pricing(input/output per 1M)=0.5/3, providers=google, supported_regions=global, multimodal=true
• gemini-2.5-flash-image: format=google, flavor=chat, displayName=Gemini 2.5 Flash Image, max_input_tokens=65536, max_output_tokens=32768, pricing(input/output per 1M)=0.3/2.5, providers=google, supported_regions=global, multimodal=true
• gemini-embedding-2-preview: format=google, flavor=embedding, displayName=Gemini Embedding 2 Preview, max_input_tokens=8192, max_output_tokens=n/a, pricing(input/output per 1M)=0.2/?, providers=google, multimodal=true
• gemini-2.5-computer-use-preview-10-2025: format=google, flavor=chat, displayName=Gemini 2.5 Computer Use Preview, max_input_tokens=128000, max_output_tokens=64000, pricing(input/output per 1M)=1.25/10, providers=google, multimodal=true

Opened #503 to apply the catalog update.

[github-actions]

Prepared catalog updates for gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025. Added models: gemini-3.1-flash-image-preview, gemini-2.5-flash-image, gemini-embedding-2-preview, gemini-2.5-computer-use-preview-10-2025.

Verification sources: https://ai.google.dev/gemini-api/docs/pricing, https://cloud.google.com/vertex-ai/generative-ai/pricing, https://ai.google.dev/gemini-api/docs/models, https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-1-flash-image, https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-flash-image, https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2-preview, https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025, https://ai.google.dev/gemini-api/docs/embeddings
Verified metadata applied:

• gemini-3.1-flash-image-preview: format=google, flavor=chat, displayName=Gemini 3.1 Flash Image Preview, max_input_tokens=131072, max_output_tokens=32768, pricing(input/output per 1M)=0.5/3, providers=google|vertex, supported_regions=global, multimodal=true
• gemini-2.5-flash-image: format=google, flavor=chat, displayName=Gemini 2.5 Flash Image, max_input_tokens=32768, max_output_tokens=32768, pricing(input/output per 1M)=0.3/2.5, providers=google|vertex, supported_regions=global|europe-central2|europe-north1|europe-southwest1|europe-west1|europe-west4|europe-west8|us-central1|us-east1|us-east4|us-east5|us-south1|us-west1|us-west4, multimodal=true
• gemini-embedding-2-preview: format=google, flavor=embedding, displayName=Gemini Embedding 2 Preview, max_input_tokens=8192, max_output_tokens=n/a, pricing(input/output per 1M)=0.2/?, providers=google|vertex, multimodal=true
• gemini-2.5-computer-use-preview-10-2025: format=google, flavor=chat, displayName=Gemini 2.5 Computer Use Preview (10-2025), max_input_tokens=128000, max_output_tokens=64000, pricing(input/output per 1M)=1.25/10, providers=google|vertex, multimodal=true

Opened #503 to apply the catalog update.