DeepSeek V4 Pro 0813 vs MiniMax M3
Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.
At a glance
Generated from the rows below
Choose DeepSeek V4 Pro 0813 for
- The highest Epoch Capabilities Index (155.9)
Choose MiniMax M3 for
- The lowest cost per typical request ($0.0009)
- The only one that takes images, video
- The longest output: 1,048,576 tokens
Overview
Pricing
Prices on the route and tier chosen under each model
What will it cost?
Estimate a month of requests on the route and tier chosen for each model
Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.
Performance
Live gateway traffic
Activity
Tokens sent through Phaseo each day over the last 30 days
None of these models has had traffic through Phaseo in the last 30 days.
Features
Features from the parameters Phaseo routes support
Benchmarks
Only results that two or more of the selected models report get a row
Epoch Capabilities Index Independent
Higher is better · dot is the estimate, band is the 95% confidence interval · Epoch AI, CC BY 4.0
Artificial Analysis Intelligence Index Independent
Higher is better · at Max effort · 1 of 2 models tested
Where they rank
The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.
Artificial Analysis Intelligence Index42 models ranked
- #1Claude Opus 5.558.4
- #2GPT-6 Astra56.9
- #3GPT-6.1 Sol54.5
- #4Claude Sonnet 5.554.2
- #5GPT-6.1 Terra51.0
- #28DeepSeek V4 Pro 081323.1
- #30MiniMax M318.7
Artificial Analysis Coding Index171 models ranked
- #1Claude Fable 5.181.6
- #2GPT 5.6 Sol78.3
- #3Claude Opus 578.0
- #4GPT-6 Astra77.1
- #5Grok 4.676.8
- #30DeepSeek V4 Pro 081368.8
- #44MiniMax M358.6
Artificial Analysis Agentic Index112 models ranked
- #1Claude Fable 5.157.9
- #2Claude Opus 556.5
- #3Qwen 3.8 Max 090256.0
- #4Muse Spark 1.355.5
- #5Qwen 3.8 Flash Next53.6
- #22DeepSeek V4 Pro 081341.3
- #31MiniMax M329.5
Epoch Capabilities Index164 models ranked
- #1GPT-6 Astra169.1
- #2Claude Opus 5.5168.4
- #3GPT-6.1 Terra168.1
- #4GPT-6.1 Sol167.8
- #5Claude Sonnet 5.5166.7
- #34DeepSeek V4 Pro 0813155.9
- #71MiniMax M3146.9
Lab-reported results come from each lab’s own launch materials and may use different settings. Independent results come from third-party evaluators.
Providers
Routes Phaseo serves today, standard-tier prices per 1M tokens
| Provider | Input | Output | Cache read | Context window | Max output | Tiers |
|---|---|---|---|---|---|---|
| $0.561 | $1.683 | $0.0187 | 1,000,000 | 393,216 | Standard | |
 | $0.66 | $1.98 | $0.022 | 1,000,000 | 384,000 | Standard |
 | $1.056 | $3.168 | $0.0352 | 1,000,000 | – | Standard |
 | $1.31 | $3.96 | $0.044 | 1,000,000 | 393,216 | Standard |
 | $1.32 | $3.96 | $0.132 | 1,048,576 | 393,216 | Standard |
 | $1.32 | $3.96 | $0.13 | 1,048,576 | – | Standard, Batch, Flex |
 | $1.32 | $3.96 | – | 1,000,000 | 393,216 | Standard |
 | $1.32 | $3.96 | $0.044 | 1,048,576 | 131,072 | Standard |
 | $1.32 | $3.96 | $0.044 | 1,048,576 | 393,216 | Standard |
 | $1.32 | $3.96 | $0.13 | 1,048,576 | – | Standard |
 | $1.65 | $4.95 | $0.165 | 1,000,000 | 32,768 | Standard |
- Avian
- Input
- $0.561
- Output
- $1.683
- Context window
- 1,000,000
Standard
- DeepSeek
- Input
- $0.66
- Output
- $1.98
- Context window
- 1,000,000
Standard
- GMICloud
- Input
- $1.056
- Output
- $3.168
- Context window
- 1,000,000
Standard
- CoreWeave Forge
- Input
- $1.31
- Output
- $3.96
- Context window
- 1,000,000
Standard
- AtlasCloud
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,048,576
Standard
- Doubleword
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,048,576
Standard, Batch, Flex
- EmpirioLabs AI
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,000,000
Standard
- Inference.net
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,048,576
Standard
- NovitaAI
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,048,576
Standard
- Together
- Input
- $1.32
- Output
- $3.96
- Context window
- 1,048,576
Standard
- Venice
- Input
- $1.65
- Output
- $4.95
- Context window
- 1,000,000
Standard
Standard-tier prices. The first row is the cheapest route; pick another under the model’s name at the top.
Also listed, not routed by Phaseo: 10 providers
Abacus, Arcee AI, Baseten, CrofAI, DigitalOcean, Fireworks, ModelScope, OpenRouter, OrcaRouter, Requesty
Shown for reference: other gateways’ listings and routes Phaseo has retired or disabled.
Details
DeepSeek V4 Pro 0813 vs MiniMax M3: side-by-side summary
DeepSeek V4 Pro 0813 and MiniMax M3 are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.
DeepSeek V4 Pro 0813 is from DeepSeek. It has a 1,000,000-token context window. On its cheapest route it costs $0.561 per 1M input tokens and $1.683 per 1M output tokens.
MiniMax M3 is from MiniMax. It has a 1,000,000-token context window. On its cheapest route it costs $0.23 per 1M input tokens and $0.96 per 1M output tokens.
DeepSeek V4 Pro 0813 model details, providers and pricingMiniMax M3 model details, providers and pricing
DeepSeek V4 Pro 0813 vs MiniMax M3 at a glance
| Attribute | DeepSeek V4 Pro 0813 | MiniMax M3 |
|---|---|---|
| Lab | DeepSeek | MiniMax |
| Input price per 1M tokens | $0.561 | $0.23 |
| Output price per 1M tokens | $1.683 | $0.96 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 384,000 tokens | 1,048,576 tokens |
| Artificial Analysis Intelligence Index | 23.1 (#28) | 18.7 (#30) |
Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.
Frequently asked questions
Which is cheaper, DeepSeek V4 Pro 0813 or MiniMax M3?
MiniMax M3 is cheaper for both input and output tokens. DeepSeek V4 Pro 0813 costs $0.561 per 1M input tokens and $1.683 per 1M output tokens; MiniMax M3 costs $0.23 and $0.96, each on its cheapest standard route on Phaseo.
Which has the longer context window, DeepSeek V4 Pro 0813 or MiniMax M3?
Both have a 1,000,000-token context window.
Which scores higher on the Artificial Analysis Intelligence Index, DeepSeek V4 Pro 0813 or MiniMax M3?
DeepSeek V4 Pro 0813 scores higher on the Artificial Analysis Intelligence Index. DeepSeek V4 Pro 0813 scores 23.1, ranked #28 of 42. MiniMax M3 scores 18.7, ranked #30 of 42.
Can I use DeepSeek V4 Pro 0813 and MiniMax M3 through one API?
Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.