Databricks models & pricing
Databricks hosts 71 models (65 with public pricing) covering 3 modalities. Mosaic AI Model Serving — Llama, DBRX, Claude on Databricks with Unity Catalog governance. Cheapest input starts at $0.0200/M tokens; the most premium goes up to $30.00/M. Use Future AGI's Agent Command Center to route any Databricks model with cost-optimized fallback and unified observability.
71
chat 65
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| GPT-5 nano | $0.0500/M | $0.400/M | $0.137/M | 272,000 | tools · cache |
| gpt-oss 20B | $0.0700/M | $0.300/M | $0.128/M | 131,072 | |
| DeepSeek V4 Flash 0731 | $0.140/M | $0.280/M | $0.175/M | 1,000,000 | tools · reasoning · cache |
| Gemma 3 12B | $0.150/M | $0.500/M | $0.238/M | 128,000 | |
| GLM 5.3 Flash | $0.150/M | $0.500/M | $0.238/M | 1,048,576 | tools · vision · reasoning · cache |
| gpt-oss 120B | $0.150/M | $0.600/M | $0.263/M | 131,072 | |
| Llama 3.1 8B Instruct | $0.150/M | $0.450/M | $0.225/M | 200,000 | |
| Qwen3 Next 80B A3B Instruct | $0.150/M | $1.20/M | $0.413/M | — | tools |
| GPT-5.4 nano | $0.200/M | $1.25/M | $0.462/M | 272,000 | tools · vision · reasoning · cache |
| Qwen35 122B A10B | $0.220/M | $2.20/M | $0.715/M | 262,144 | tools · reasoning |
| GPT-5 mini | $0.250/M | $2.00/M | $0.687/M | 272,000 | tools · cache |
| Gemini 2.5 Flash Deprecated | $0.300/M | $2.50/M | $0.850/M | 1,048,576 | tools · vision · reasoning · audio · cache |
| Gemini 3.1 Flash Lite | $0.312/M | $1.88/M | $0.703/M | 1,048,576 | tools · vision · audio · cache |
| Gemini 3.5 Flash Lite | $0.375/M | $3.13/M | $1.06/M | 1,048,576 | tools · vision · reasoning · cache |
| Llama 2 70B Chat | $0.500/M | $1.50/M | $0.750/M | 4,096 | |
| Llama 4 Maverick | $0.500/M | $1.50/M | $0.750/M | 128,000 | |
| Llama 3.3 70B Instruct | $0.500/M | $1.50/M | $0.750/M | 128,000 | |
| Mixtral 8×7B Instruct | $0.500/M | $1.00/M | $0.625/M | 4,096 | |
| Mpt 7B Instruct | $0.500/M | — | — | 8,192 | |
| Gemini 3 Flash | $0.625/M | $3.75/M | $1.41/M | 1,048,576 | tools · vision · audio · cache |
| GPT-5.4 mini | $0.750/M | $4.50/M | $1.69/M | 272,000 | tools · vision · reasoning · cache |
| Claude Haiku 4.5 | $1.00/M | $5.00/M | $2.00/M | 200,000 | tools · reasoning · cache |
| GPT-5.6 Luna | $1.00/M | $6.00/M | $2.25/M | 922,000 | tools · vision · reasoning · cache |
| Inkling | $1.00/M | $4.05/M | $1.76/M | 1,000,000 | tools · vision · reasoning · cache |
| Llama 3 70B Instruct | $1.00/M | $3.00/M | $1.50/M | 128,000 | |
| Mpt 30B Instruct | $1.00/M | $1.00/M | $1.00/M | 8,192 | |
| Gemini 2.5 Pro Deprecated | $1.25/M | $10.00/M | $3.44/M | 1,048,576 | tools · vision · reasoning · audio · cache |
| GPT-5 | $1.25/M | $10.00/M | $3.44/M | 272,000 | tools · cache |
| GPT-5.1 | $1.25/M | $10.00/M | $3.44/M | 272,000 | tools · cache |
| DeepSeek V4 Pro 0813 | $1.32/M | $3.96/M | $1.98/M | 1,000,000 | tools · reasoning · cache |
| GLM 5.2 | $1.40/M | $4.40/M | $2.15/M | 1,000,000 | tools · reasoning · cache |
| GLM 5.3 | $1.40/M | $4.40/M | $2.15/M | 1,048,576 | tools · reasoning · cache |
| GPT-5.2 | $1.75/M | $14.00/M | $4.81/M | 272,000 | tools · cache |
| Gemini 3.5 Flash | $1.88/M | $11.25/M | $4.22/M | 1,048,576 | tools · vision · reasoning · cache |
| Gemini 3.6 Flash | $1.88/M | $9.38/M | $3.75/M | 1,048,576 | tools · vision · reasoning · cache |
| Gemini 3.1 Pro | $2.50/M | $15.00/M | $5.62/M | 1,048,576 | tools · vision · reasoning · audio · cache |
| Gemini 3 Pro | $2.50/M | $15.00/M | $5.62/M | 1,048,576 | tools · cache |
| GPT-5.4 | $2.50/M | $15.00/M | $5.62/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.6 Terra | $2.50/M | $15.00/M | $5.62/M | 922,000 | tools · vision · reasoning · cache |
| Grok 4.6 | $2.50/M | $7.50/M | $3.75/M | 500,000 | tools · reasoning · cache |
| Claude 3.7 Sonnet | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · reasoning |
| Claude Sonnet 4 Deprecated | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · reasoning · cache |
| Claude Sonnet 4.1 | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · reasoning · cache |
| Claude Sonnet 4.5 | $3.00/M | $15.00/M | $6.00/M | 200,000 | tools · reasoning · cache |
| Claude Sonnet 4.6 | $3.00/M | $15.00/M | $6.00/M | 1,000,000 | tools · reasoning · cache |
| Claude Sonnet 5 | $3.00/M | $15.00/M | $6.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 5.5 | $4.00/M | $20.00/M | $8.00/M | 1,000,000 | tools · vision · reasoning · cache |
| GPT-5.6 Sol | $4.00/M | $20.00/M | $8.00/M | 922,000 | tools · vision · reasoning · cache |
| Claude Opus 4.5 | $5.00/M | $25.00/M | $10.00/M | 200,000 | tools · reasoning · cache |
| Claude Opus 4.6 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · reasoning · cache |
| Claude Opus 4.7 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 4.8 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 5 | $5.00/M | $25.00/M | $10.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Llama 3.1 405B Instruct | $5.00/M | $15.00/M | $7.50/M | 128,000 | |
| Claude Fable 5 | $10.00/M | $50.00/M | $20.00/M | 1,000,000 | tools · reasoning · cache |
| Claude Fable 5.1 | $10.00/M | $50.00/M | $20.00/M | 1,000,000 | tools · vision · reasoning · cache |
| Claude Opus 4 | $15.00/M | $75.00/M | $30.00/M | 200,000 | tools · reasoning · cache |
| Claude Opus 4.1 | $15.00/M | $75.00/M | $30.00/M | 200,000 | tools · reasoning · cache |
| DeepSeek V4 Flash 0731 | — | — | — | — | |
| Gemini 3 Pro Image | — | — | — | 65,536 | vision |
| Gemini 3.1 Flash Image | — | — | — | 131,072 | vision |
| Gemini 3.7 Flash | — | — | — | 1,048,576 | tools · vision · reasoning |
| Gemini 3.8 Flash | — | — | — | 1,048,576 | tools · vision · reasoning |
| Kimi K3 | — | — | — | — |
embedding 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Qwen3 Embedding 0 6B | $0.0200/M | — | — | 32,768 | |
| BGE Large En | $0.100/M | — | — | 512 | |
| GTE Large En | $0.130/M | — | — | 8,192 |
responses 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| GPT-5.3 Codex | $1.75/M | $14.00/M | $4.81/M | 272,000 | tools · cache |
| GPT-5.5 | $5.00/M | $30.00/M | $11.25/M | 922,000 | tools · vision · reasoning · cache |
| GPT-5.5 Pro | $30.00/M | $180/M | $67.50/M | 922,000 | tools · vision · reasoning · cache |
FAQ
How many Databricks models are there?
71 Databricks models are listed across 3 modalities on this page. 65 have public per-token pricing.
How is Databricks pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Databricks model is cheapest?
Input pricing on Databricks starts at $0.0200 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Databricks via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Databricks target, and call Databricks models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any Databricks model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.