Modal - $30/Month Free Compute Credits
Source: https://modal.com/pricing
Description
Create account to comment on specific lines or Sign in
+ 1 Modal gives every Starter plan user $30 in free compute credits each month with no monthly fee and no credit card required. You pay only for actual compute time — by the CPU cycle, billed per second — so bursty workloads like inference, batch jobs, and fine-tuning cost a fraction of what reserved instances charge. Modal supports a wide range of NVIDIA GPUs (T4 through B200), serverless functions, scheduled cron jobs, web endpoints, and persistent volumes. Credits reset monthly and never roll over.
No comments on this line yet.
+ 2
No comments on this line yet.
+
3
No comments on this line yet.
+ 4
No comments on this line yet.
+ 6
No comments on this line yet.
+ 7 1. Go to modal.com/signup
No comments on this line yet.
+ 8 2. Click "Continue with GitHub", "Continue with Google", or use SSO — no email/password form, just OAuth
No comments on this line yet.
+
9
3. Authorize the Modal app (GitHub requests user:email and optionally read:org for workspace invites — it does not access your repos)
No comments on this line yet.
+ 10 4. Your workspace is created immediately with $30 in free monthly credits
No comments on this line yet.
+
11
5. Install the Python package locally: pip install modal
No comments on this line yet.
+
12
6. Run modal setup in your terminal — this opens a browser tab to authenticate your CLI with a token
No comments on this line yet.
+
13
7. You are ready to deploy — run modal run your_script.py to test
No comments on this line yet.
+ 14
No comments on this line yet.
+ 15 Important:
No comments on this line yet.
+ 16 • No credit card required for the Starter plan. You only need to add billing if you exceed $30/month
No comments on this line yet.
+ 17 • The $30 credit resets every month — unused credits do not roll over
No comments on this line yet.
+ 18 • One workspace is created per signup; you can invite up to 3 seats on the Starter plan
No comments on this line yet.
+ 19 • Modal runs on top of major cloud providers — you do not need your own AWS/GCP account
No comments on this line yet.
+ 20
No comments on this line yet.
+
21
No comments on this line yet.
+ 22
No comments on this line yet.
+ 24
No comments on this line yet.
+ 25 Modal charges per second with no minimum commitment. Here is what the main resources cost:
No comments on this line yet.
+ 26
No comments on this line yet.
+ 28
No comments on this line yet.
+ 29 GPUPer SecondApprox. Per Hour~Free Hours/Month ($30)
No comments on this line yet.
+ 30 NVIDIA T4 (16 GB)$0.000164$0.59~50 h
No comments on this line yet.
+ 31 NVIDIA L4 (24 GB)$0.000222$0.80~37 h
No comments on this line yet.
+ 32 NVIDIA A10G (24 GB)$0.000306$1.10~27 h
No comments on this line yet.
+ 33 NVIDIA L40S (48 GB)$0.000542$1.95~15 h
No comments on this line yet.
+ 34 NVIDIA A100 40 GB$0.000583$2.10~14 h
No comments on this line yet.
+ 35 NVIDIA A100 80 GB$0.000694$2.50~12 h
No comments on this line yet.
+ 36 NVIDIA H100 (80 GB)$0.001097$3.95~7.5 h
No comments on this line yet.
+ 37 NVIDIA H200 (141 GB)$0.001261$4.54~6.6 h
No comments on this line yet.
+ 38 NVIDIA B200 (192 GB)$0.001736$6.25~4.8 h
No comments on this line yet.
+ 39
No comments on this line yet.
+ 41
No comments on this line yet.
+ 42 ResourcePer SecondApprox. Per Hour
No comments on this line yet.
+ 43 CPU$0.0000131 / core$0.047 / core
No comments on this line yet.
+ 44 Memory$0.00000222 / GiB$0.008 / GiB
No comments on this line yet.
+ 45 Sandbox/Notebook CPU$0.00003942 / core$0.142 / core
No comments on this line yet.
+ 46 Sandbox/Notebook Memory$0.00000672 / GiB$0.024 / GiB
No comments on this line yet.
+ 47
No comments on this line yet.
+ 48 Minimum CPU allocation is 0.125 cores. There are no idle charges — when your function is not running, you pay nothing.
No comments on this line yet.
+ 49
No comments on this line yet.
+
50
No comments on this line yet.
+ 51
No comments on this line yet.
+ 53
No comments on this line yet.
+ 54 The free Starter plan has the following concurrency and deployment limits:
No comments on this line yet.
+ 55
No comments on this line yet.
+ 56 ResourceStarter Limit
No comments on this line yet.
+ 57 Concurrent containers100
No comments on this line yet.
+ 58 GPU concurrency10
No comments on this line yet.
+ 59 Deployed cron jobs5
No comments on this line yet.
+ 60 Deployed web endpoints8
No comments on this line yet.
+ 61 Log retention1 day
No comments on this line yet.
+ 62 Workspace seats3
No comments on this line yet.
+ 63 Deployment rollback versions3
No comments on this line yet.
+ 64 Custom domainsNot available
No comments on this line yet.
+ 65
No comments on this line yet.
+ 66 These limits are sufficient for individual developers and small teams running experiments, inference endpoints, or periodic batch jobs.
No comments on this line yet.
+ 67
No comments on this line yet.
+
68
No comments on this line yet.
+ 69
No comments on this line yet.
+ 71
No comments on this line yet.
+
72
• Serverless Functions — decorate any Python function with @app.function() and Modal handles containerization, scaling, and GPU attachment automatically
No comments on this line yet.
+ 73 • Per-Second Autoscaling — scales from zero to hundreds of GPUs in seconds, then back to zero when idle
No comments on this line yet.
+ 74 • Sub-Second Cold Starts — custom Rust-based runtime starts GPU containers in ~1-2 seconds
No comments on this line yet.
+
75
• Web Endpoints — expose functions as HTTPS endpoints with @app.web_endpoint() for serving models or APIs
No comments on this line yet.
+
76
• Cron Jobs — schedule recurring tasks with @app.cron() syntax
No comments on this line yet.
+ 77 • Volumes — persistent distributed storage (up to 1 TiB per file, ~2.5 GB/s bandwidth) for model weights, datasets, and artifacts
No comments on this line yet.
+ 78 • Cloud Bucket Mounts — mount S3 or GCS buckets directly as file systems (Cloudflare R2 recommended for zero egress fees)
No comments on this line yet.
+ 79 • Secrets — securely inject API keys and credentials as environment variables
No comments on this line yet.
+ 80 • Sandboxes — run untrusted or AI-generated code in isolated containers
No comments on this line yet.
+ 81 • Notebooks — GPU-backed Jupyter notebooks with zero cold-boot penalty
No comments on this line yet.
+ 82 • Infrastructure as Code — define container images, GPU requirements, and dependencies in Python — no YAML, no Dockerfiles required
No comments on this line yet.
+ 83
No comments on this line yet.
+
84
No comments on this line yet.
+ 85
No comments on this line yet.
+ 87
No comments on this line yet.
+ 88 FeatureStarter ($0/mo)Team ($250/mo)Enterprise (Custom)
No comments on this line yet.
+ 89 Free monthly credits$30$100Custom
No comments on this line yet.
+ 90 Containers1001,000Custom
No comments on this line yet.
+ 91 GPU concurrency1050Custom
No comments on this line yet.
+ 92 Cron jobs5UnlimitedUnlimited
No comments on this line yet.
+ 93 Web endpoints8UnlimitedUnlimited
No comments on this line yet.
+ 94 Log retention1 day30 daysCustom
No comments on this line yet.
+ 95 Seats3UnlimitedUnlimited
No comments on this line yet.
+ 96 Custom domainsNoYesYes
No comments on this line yet.
+ 97 Static IP proxyNoYesYes
No comments on this line yet.
+ 98 Okta SSONoNoYes
No comments on this line yet.
+ 99 SupportCommunityCommunityPrivate Slack + ML engineering
No comments on this line yet.
+ 100
No comments on this line yet.
+
101
No comments on this line yet.
+ 102
No comments on this line yet.
+ 104
No comments on this line yet.
+ 106
No comments on this line yet.
+ 107 TierCreditsRequirements
No comments on this line yet.
+ 108 BootstrappedUp to $5,000Full-time team, raised < $500K outside Modal's VC network, active website
No comments on this line yet.
+ 109 Seed to Series AUp to $25,000Raised up to $30M via Modal's partner VC network (YC, a16z, Sequoia, Khosla, etc.)
No comments on this line yet.
+ 110 Series B+CustomRaised > $30M or post-Series B, VC from partner network
No comments on this line yet.
+ 111
No comments on this line yet.
+ 112 Apply at modal.com/startups. Credits are granted once per tier.
No comments on this line yet.
+ 113
No comments on this line yet.
+ 115
No comments on this line yet.
+ 116 Graduate students, labs, and researchers can apply for up to $10,000 in free compute credits for research projects. Credits typically expire after conference submission results are finalized and are granted once per conference. Educators should contact partnerships@modal.com for dedicated teaching programs.
No comments on this line yet.
+ 117
No comments on this line yet.
+ 118 Apply at modal.com/academics.
No comments on this line yet.
+ 119
No comments on this line yet.
+
120
No comments on this line yet.
+ 121
No comments on this line yet.
+ 123
No comments on this line yet.
+ 124 • No billing surprise risk on Starter — if you exceed $30 without a payment method, your workloads stop rather than incurring charges. You must explicitly add billing to go beyond the free tier
No comments on this line yet.
+ 125 • AWS/GCP Marketplace — if you have committed cloud spend, you can route Modal usage through the AWS or GCP Marketplace to draw from existing commitments
No comments on this line yet.
+ 126 • Model weights workflow — store large model files in a Modal Volume and mount them into functions to avoid re-downloading on each cold start
No comments on this line yet.
+ 127 • Cloudflare R2 for datasets — Modal recommends R2 over S3 for large dataset storage because Cloudflare charges zero egress fees
No comments on this line yet.
+ 128 • Python-first, but not Python-only — the primary SDK is Python, but JavaScript/TypeScript and Go SDKs are available for calling functions, managing sandboxes, and interacting with resources
No comments on this line yet.
+ 129 • No Docker required locally — Modal builds container images in the cloud from your Python code; you never need to write a Dockerfile
No comments on this line yet.
+ 130 • Compare with alternatives — for always-on workloads running 24/7, reserved GPU instances (RunPod, Lambda, etc.) may be cheaper; Modal shines for bursty, intermittent, or autoscaling workloads
No comments on this line yet.
+ 131
No comments on this line yet.
+
132
No comments on this line yet.
+ 133
No comments on this line yet.
+ 134 Sources:
No comments on this line yet.
+ 135 • Modal Pricing
No comments on this line yet.
+ 136 • Modal Signup
No comments on this line yet.
+ 137 • Modal Documentation Guide
No comments on this line yet.
+ 138 • Modal Account Setup
No comments on this line yet.
+ 139 • Modal for Startups
No comments on this line yet.
+ 140 • Modal for Academics
No comments on this line yet.
+ 141 • Modal Volumes Documentation
No comments on this line yet.
+ 142 • Modal on AWS Marketplace
No comments on this line yet.