Databricks Pricing
Databricks charges from $0.200 per 1 million output tokens, depending on the model. GPT OSS 20B is the cheapest at $0.200/1M output and $0.050/1M input; its current flagship GPT-5.6 Sol costs $30.00/1M output. The largest context window is 1.1M tokens (GPT-5.4). Prices are USD, current as of October 12, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.050/1M
Databricks GPT 5 Nano
Cheapest output
$0.200/1M
GPT OSS 20B
Longest context
1.1M
GPT-5.4
Models priced
81
Avg $13.17/1M output
Pricing by model
All prices in USD per 1 million tokens. Showing 80 of 81 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| GPT OSS 20B ReasoningTools | $0.050 | $0.200 | 131K |
| Databricks DeepSeek V4 Flash 0731 | $0.140 | $0.280 | 1.0M |
| GPT OSS 120B ReasoningTools | $0.072 | $0.280 | 131K |
| Databricks GPT Oss 20B | $0.070 | $0.300 | 131K |
| Databricks GPT 5 Nano | $0.050 | $0.400 | 272K |
| GPT-5 Nano VisionReasoningToolsCache | $0.050 | $0.400 | 400K |
| Databricks Meta Llama 3.1 8B Instruct | $0.150 | $0.450 | 200K |
| Databricks Gemma 3 12B | $0.150 | $0.500 | 128K |
| Databricks Glm 5.3 Flash | $0.150 | $0.500 | 1.0M |
| Databricks GPT Oss 120B | $0.150 | $0.600 | 131K |
| Databricks Qwen3 Next 80B A3b Instruct | $0.150 | $1.20 | 0 |
| Databricks GPT 5.4 Nano | $0.200 | $1.25 | 272K |
| GPT-5.4 nano VisionReasoningToolsCache | $0.200 | $1.25 | 400K |
| Gemini 3.1 Flash Lite Preview VisionReasoningToolsCache | $0.250 | $1.50 | 1.0M |
| Databricks Llama 4 Maverick | $0.500 | $1.50 | 128K |
| Databricks Meta Llama 3.3 70B Instruct | $0.500 | $1.50 | 128K |
| Databricks Gemini 3.1 Flash Lite | $0.312 | $1.88 | 1.0M |
| Databricks GPT 5 Mini | $0.250 | $2.00 | 272K |
| GPT-5 Mini VisionReasoningToolsCache | $0.250 | $2.00 | 400K |
| Databricks Qwen35 122B A10b | $0.220 | $2.20 | 262K |
| Databricks Gemini 2.5 Flash | $0.300 | $2.50 | 1.0M |
| Gemini 2.5 Flash VisionReasoningToolsCache | $0.300 | $2.50 | 1.0M |
| Gemini 3 Flash Preview VisionReasoningToolsCache | $0.500 | $3.00 | 1.0M |
| Databricks Gemini 3.5 Flash Lite | $0.375 | $3.13 | 1.0M |
| Databricks Gemini 3 Flash | $0.625 | $3.75 | 1.0M |
| Databricks DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1.0M |
| Kimi K2.7 Code VisionReasoningToolsCache | $0.950 | $4.00 | 262K |
| Databricks Inkling | $1.00 | $4.05 | 1.0M |
| Databricks Glm 5.2 | $1.40 | $4.40 | 1.0M |
| Databricks Glm 5.3 | $1.40 | $4.40 | 1.0M |
| GLM-5.2 ReasoningToolsCache | $1.40 | $4.40 | 1.0M |
| GPT-5.4 mini VisionReasoningToolsCache | $0.750 | $4.50 | 400K |
| Databricks GPT 5.4 Mini | $0.750 | $4.50 | 272K |
| Claude Haiku 4.5 VisionReasoningToolsCache | $1.00 | $5.00 | 200K |
| Databricks Claude Haiku 4.5 | $1.00 | $5.00 | 200K |
| Databricks GPT 5.6 Luna | $1.00 | $6.00 | 922K |
| GPT-5.6 Luna VisionReasoningToolsCache | $1.00 | $6.00 | 400K |
| Databricks Grok 4.6 | $2.50 | $7.50 | 500K |
| Databricks Gemini 3.6 Flash | $1.88 | $9.38 | 1.0M |
| Databricks Gemini 2.5 Pro | $1.25 | $10.00 | 1.0M |
| Databricks GPT 5 | $1.25 | $10.00 | 272K |
| Databricks GPT 5.1 | $1.25 | $10.00 | 272K |
| Gemini 2.5 Pro VisionReasoningToolsCache | $1.25 | $10.00 | 1.0M |
| GPT-5 VisionReasoningToolsCache | $1.25 | $10.00 | 400K |
| GPT-5.1 VisionReasoningToolsCache | $1.25 | $10.00 | 400K |
| Databricks Gemini 3.5 Flash | $1.88 | $11.25 | 1.0M |
| Gemini 3 Pro Preview VisionReasoningToolsCache | $2.00 | $12.00 | 1.0M |
| Gemini 3.1 Pro Preview Custom Tools VisionReasoningToolsCache | $2.00 | $12.00 | 1.0M |
| Databricks GPT 5.2 | $1.75 | $14.00 | 272K |
| GPT-5.2 VisionReasoningToolsCache | $1.75 | $14.00 | 400K |
| Claude Sonnet 4.5 VisionReasoningToolsCache | $3.00 | $15.00 | 200K |
| Claude Sonnet 4.6 VisionReasoningToolsCache | $3.00 | $15.00 | 1.0M |
| GPT-5.4 VisionReasoningToolsCache | $2.50 | $15.00 | 1.1M |
| GPT-5.6 Terra VisionReasoningToolsCache | $2.50 | $15.00 | 1.1M |
| Databricks Claude Sonnet 4 | $3.00 | $15.00 | 200K |
| Databricks Claude Sonnet 4.1 | $3.00 | $15.00 | 200K |
| Databricks Claude Sonnet 4.5 | $3.00 | $15.00 | 200K |
| Databricks Claude Sonnet 4.6 | $3.00 | $15.00 | 1.0M |
| Databricks Claude Sonnet 5 | $3.00 | $15.00 | 1.0M |
| Databricks Gemini 3 Pro | $2.50 | $15.00 | 1.0M |
| Databricks Gemini 3.1 Pro | $2.50 | $15.00 | 1.0M |
| Databricks GPT 5.4 | $2.50 | $15.00 | 922K |
| Databricks GPT 5.6 Terra | $2.50 | $15.00 | 922K |
| Databricks Kimi K3 | $3.00 | $15.00 | 1.0M |
| Databricks Claude Opus 5.5 | $4.00 | $20.00 | 1.0M |
| Databricks GPT 5.6 Sol | $4.00 | $20.00 | 922K |
| Claude Opus 4.5 VisionReasoningToolsCache | $5.00 | $25.00 | 200K |
| Claude Opus 4.6 VisionReasoningToolsCache | $5.00 | $25.00 | 1.0M |
| Claude Opus 4.7 VisionReasoningToolsCache | $5.00 | $25.00 | 1.0M |
| Databricks Claude Opus 4.5 | $5.00 | $25.00 | 200K |
| Databricks Claude Opus 4.6 | $5.00 | $25.00 | 1.0M |
| Databricks Claude Opus 4.7 | $5.00 | $25.00 | 1.0M |
| Databricks Claude Opus 4.8 | $5.00 | $25.00 | 1.0M |
| Databricks Claude Opus 5 | $5.00 | $25.00 | 1.0M |
| GPT-5.5 VisionReasoningToolsCache | $5.00 | $30.00 | 1.1M |
| GPT-5.6 Sol VisionReasoningToolsCache | $5.00 | $30.00 | 1.1M |
| Databricks Claude Fable 5 | $10.00 | $50.00 | 1.0M |
| Databricks Claude Fable 5.1 | $10.00 | $50.00 | 1.0M |
| Claude Opus 4.1 VisionReasoningToolsCache | $15.00 | $75.00 | 200K |
| Databricks Claude Opus 4.1 | $15.00 | $75.00 | 200K |
Frequently asked questions
How much does Databricks cost per 1M tokens?
Databricks pricing starts at $0.200 per 1 million output tokens (GPT OSS 20B) across 81 models, with its current flagship GPT-5.6 Sol at $30.00. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest Databricks model?
GPT OSS 20B is the cheapest Databricks model on output tokens at $0.200 per 1M, while Databricks GPT 5 Nano is cheapest on input at $0.050 per 1M. Which wins for you depends on your input-to-output ratio.
What is the largest Databricks context window?
GPT-5.4 has the largest context window in the Databricks catalog at 1.1M input tokens, with up to 128K output tokens per response.
Does Databricks support prompt caching?
Yes. GPT-5 Nano reads cached input at $0.0050 per 1M tokens, against $0.050 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.
Which Databricks models support reasoning or vision?
The Databricks catalog includes 29 reasoning models, 26 vision models, 29 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.
How do I calculate my actual Databricks bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator