Modal
Managed inference API — 10 shared-endpoint models with per-token pricing
Modal Shared Endpoints serve a fixed catalog of models from Modal-managed pools. Modal manages the hardware and autoscaling, and usage is billed per token. Shared Endpoints have model-specific concurrency limits on concurrent in-flight requests. Prices are published rates from modal.com/docs/guide/supported-models.md, re-read 2026-10-31.
Modal Shared Endpoints provide managed per-token inference on a fixed 10-model catalog with published cached-input pricing and no infrastructure to manage.
- Managed hardware and autoscaling — no infrastructure to operate
- Published per-token rates including cached-input pricing
- OpenAI-style per-token billing across all 10 models
- Cached-input pricing available on every model in the catalog
- Small fixed catalog of 10 models
- Model-specific concurrency limits on shared pools
- Prices are published rates re-read 2026-10-31, not continuously collected
Modal Models
| Model | Modality | Tier | Price | Cached /1M | TTFT | Throughput | Context | Intel. | Caps | |
|---|---|---|---|---|---|---|---|---|---|---|
glm-5-3-flash-nvfp4 GLM 5.3 | Chat | budget | $0.15/ $0.50 in / out per 1M EST Oct 2026 | $0.03 | — | — | — | — | ||
deepseek-v4-1-flash-1017 DeepSeek V4.1 | Chat | budget | $0.25/ $1.00 in / out per 1M EST Oct 2026 | $0.01 | — | — | — | — | ||
deepseek-v4-1-flash DeepSeek V4.1 | Chat | budget | $0.30/ $1.20 in / out per 1M EST Oct 2026 | $0.03 | — | — | — | — | ||
glm-5-3-flash GLM 5.3 | Chat | budget | $0.45/ $1.50 in / out per 1M EST Oct 2026 | $0.09 | — | — | — | — | ||
inkling-nvfp4 Inkling | Chat | advanced | $1.20/ $5.00 in / out per 1M EST Oct 2026 | $0.27 | — | — | — | — | ||
muse-spark-open Muse Spark | Chat | advanced | $1.25/ $4.25 in / out per 1M EST Oct 2026 | $0.15 | — | — | — | — | ||
glm-5-3 GLM 5.3 | Chat | advanced | $1.40/ $4.40 in / out per 1M EST Oct 2026 | $0.26 | — | — | — | — | ||
qwen3-8-max Qwen3.8 | Chat | advanced | $2.00/ $6.00 in / out per 1M EST Oct 2026 | $0.25 | — | — | — | — | ||
qwen3-8-max-vl Qwen3.8 | Chat | advanced | $2.00/ $6.00 in / out per 1M EST Oct 2026 | $0.25 | — | — | — | — | ||
kimi-k3 Kimi K3 | Chat | advanced | $3.00/ $15.00 in / out per 1M EST Oct 2026 | $0.30 | — | — | — | — |
Modal — Frequently Asked Questions (FAQs)
Similar Providers
Modal Reviews
All LLM Providers
Full comparison tableModal LLM pricing overview
Modal is an inference API provider that hosts open-weight and third-party large language models. Modal Shared Endpoints serve a fixed catalog of models from Modal-managed pools. Modal manages the hardware and autoscaling, and usage is billed per token. Shared Endpoints have model-specific concurrency limits on concurrent in-flight requests. Prices are published rates from modal.com/docs/guide/supported-models.md, re-read 2026-10-31. Common use cases include Inference, Cost-efficiency, Open-source, Chat. All models are accessible via a REST API compatible with standard OpenAI-style request formats, enabling drop-in integration with most LLM frameworks and orchestration tools.
Modal vs other LLM providers
Modal competes with OpenAI, Anthropic, Google, Groq, Together AI, Mistral, Cohere, and other inference API providers across dimensions of price, throughput, latency, context window, and model intelligence. Modal Shared Endpoints provide managed per-token inference on a fixed 10-model catalog with published cached-input pricing and no infrastructure to manage. Use the LLM provider comparison tool to see Modal token pricing, latency, and throughput side-by-side with any other provider. The full LLM pricing table shows all providers ranked by input token cost, output token cost, and throughput in a single sortable view.
Why choose Modal?
Modal stands out because: Modal Shared Endpoints provide managed per-token inference on a fixed 10-model catalog with published cached-input pricing and no infrastructure to manage.. The API currently offers 10 models, spanning 6 advanced, 4 budget tiers. For teams running high-volume inference workloads, prompt caching and batch API endpoints can reduce effective input token costs by 50–90% — check the context window cost guide for a full breakdown of caching economics.
Understanding Modal token pricing
Modal charges separately for input (prompt) and output (completion) tokens, priced per 1M tokens in USD. Output tokens are typically 3–5× more expensive than input tokens due to the compute cost of autoregressive generation. The cheapest {meta.name} input rate is currently $0.15/1M tokens. Prices shown are sourced from Modal's public pricing page and updated every 15 minutes. Need help estimating your spend? Read the LLM API cost calculator guide — it covers tokens, context windows, prompt caching, and batch discounts with worked examples for RAG, chat history, and document processing workloads.
Modal context window and model capabilities
Context window size directly affects both capability and cost — every token in the context window is charged as an input token. Modal's largest context window is 0 tokens. For RAG and document processing workloads, longer context windows enable richer retrieval but increase per-call costs proportionally. Prompt caching — where supported — stores the KV state of repeated prefixes and charges 75–90% less for cache hits, making it the most impactful cost optimization for applications with consistent system prompts or retrieved documents. See the LLM context window cost guide for a full analysis of how context length affects your API bill.
Self-hosted vs managed inference: when Modal makes sense
Managed inference APIs like Modal eliminate infrastructure overhead — no GPU provisioning, driver management, or model serving stack to maintain. The trade-off is cost at scale: a single H100 at ~$2.50/hr can serve ~500K tokens/min of Llama 3.3 70B, which at Modal API rates would cost significantly more per token. The break-even point depends on your request volume, latency requirements, and engineering capacity. For teams processing fewer than ~10M tokens/day, managed APIs are almost always cheaper when total cost of ownership is considered. Above that threshold, self-hosted inference on rented GPU compute typically wins on unit economics. Read the cheapest GPU cloud guide for a full break-even analysis. Historical Modal token price data is available in the LLM price history charts.
Compare Modal With Another LLM Provider
Compare Modal vs other providers
Side-by-side token pricing, latency, throughput, and context window. View all LLM provider comparisons →