fix: add Databricks models databricks-claude-opus-4-8 +2 more

[github-actions]

fix: add Databricks models databricks-claude-opus-4-8 +2 more

Closes #692

Source issue: #692

Summary

Field	Value
Provider	databricks
Primary model	databricks-claude-opus-4-8
Changed models	databricks-claude-opus-4-8 databricks-gpt-oss-120b databricks-llama-4-maverick
Added models	databricks-claude-opus-4-8 databricks-gpt-oss-120b databricks-llama-4-maverick
Updated models	None
Verification sources	1 2 3

Verified metadata

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
databricks-claude-opus-4-8	Claude Opus 4.8		databricks	openai	chat	input=1000000, output=128000	n/a	multimodal=true; reasoning=true
databricks-gpt-oss-120b	GPT-OSS 120B		databricks	openai	chat	input=128000, output=not provided	n/a	reasoning=true
databricks-llama-4-maverick	Llama 4 Maverick		databricks	openai	chat	input=1000000, output=not provided	n/a	multimodal=true

Verification notes

Verification

Official sources consulted

1. Databricks Supported Models page (https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models)

   • Verified: model IDs, context windows for claude-opus-4-8 (1M) and gpt-oss-120b (128K), supported input types (text/image), reasoning capability descriptions
   • Not published: max_output_tokens, pricing for all three models; context window for llama-4-maverick

2. Databricks Foundation Model Overview (https://docs.databricks.com/aws/en/machine-learning/model-serving/foundation-model-overview)

   • Verified: regional availability, pay-per-token availability for all three models

3. Meta HuggingFace Model Card (https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct)

   • Verified: Llama 4 Maverick context length = 1M tokens, input modalities (multilingual text and image)

4. Existing catalog entries (model_list.json)

   • Base claude-opus-4-8: max_input_tokens=1000000, max_output_tokens=128000, reasoning=true (line 2607)
   • Base gpt-oss-120b: max_input_tokens=131072, max_output_tokens=32768, reasoning=true (line 1519)
   • Bedrock meta.llama4-maverick-17b-instruct-v1:0: max_input_tokens=1000000, max_output_tokens=8000 (line 11698)

sync_models (LiteLLM) cross-check

None of the three models (databricks-claude-opus-4-8, databricks-gpt-oss-120b, databricks-llama-4-maverick) appear in the LiteLLM model_prices_and_context_window_backup.json catalog. LiteLLM does not track Databricks-specific model entries. No numeric field comparison is possible.

Fields not published or not applicable

• Pricing (all models): Databricks does not publish stable per-model pricing — omitted
• max_output_tokens (gpt-oss-120b): Not specified by Databricks; base model varies by provider — omitted
• max_output_tokens (llama-4-maverick): Not specified by Databricks; varies across providers (8000–8192) — omitted
• reasoning (llama-4-maverick): Not confirmed for Databricks-hosted version — omitted
• reasoning_budget: Not confirmed for any of these Databricks models — omitted
• deprecation_date: None of these models are deprecated
• parent: None of these models are dated snapshots or location-scoped variants of an existing base alias in model_list.json
• supported_regions: Not applicable (Databricks provider, not Vertex)

sync_models vs proposed update

sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.

Model	Field	Proposed update	sync_models	sync_models source models
databricks-claude-opus-4-8	catalog entry	present	missing	None
databricks-gpt-oss-120b	max_input_tokens	128000	131072	databricks/databricks-gpt-oss-120b
databricks-gpt-oss-120b	max_output_tokens	n/a	131072	databricks/databricks-gpt-oss-120b
databricks-gpt-oss-120b	input_cost_per_mil_tokens	n/a	0.15001	databricks/databricks-gpt-oss-120b
databricks-gpt-oss-120b	output_cost_per_mil_tokens	n/a	0.59997	databricks/databricks-gpt-oss-120b
databricks-llama-4-maverick	max_input_tokens	1000000	128000	databricks/databricks-llama-4-maverick
databricks-llama-4-maverick	max_output_tokens	n/a	128000	databricks/databricks-llama-4-maverick
databricks-llama-4-maverick	input_cost_per_mil_tokens	n/a	0.50001	databricks/databricks-llama-4-maverick
databricks-llama-4-maverick	output_cost_per_mil_tokens	n/a	1.50003	databricks/databricks-llama-4-maverick

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview, Comment	May 31, 2026 9:17am