AI Model (LLM API) · decision tool
Cheapest LLM API at your volume
Every model priced at YOUR monthly tokens from live data — including the open-weights options that undercut the big three by 10–50×.
Prices verified 2026-07-13 against official pricing pages · fit weights are our estimates (see methodology) · share the URL to share your configuration
As of Jul 2026, with 100M input tokens/month, 20 millions output tokens / month, a $50 budget for this slot, DeepSeek V4 Flash ranks first for these inputs at 84% fit and a StackSays-estimated $10.78/month (OpenAI GPT-5 Nano: 81% fit, $13.00/month). Fit weights are our estimates; prices trace to official pages. Change any input below and the verdict recomputes.
Your situation
The verdict updates as you move these.
Narrow pick — the runner-up is close
The price floor: open weights, pennies per million tokens
vs OpenAI GPT-5 Nano: fit 84% against 81%, est $10.78 against $13.00 per month
The decision, in plain words
For a solo builder at 100M input tokens/month and a $50.00/mo budget for the AI model slot, DeepSeek V4 Flash leads at 84% fit and $10.78/mo. The two rules doing the work: budget fit (~$10.78/mo is 22% of your $50/mo budget); ecosystem maturity (established — our estimate from ecosystem age, docs and hiring pool).
OpenAI GPT-5 Nano runs close (81% fit, $13.00/mo). It takes the lead if ~$13/mo is 26% of your $50/mo budget matters more to you than the current weights assume.
Honest weak spot of the pick: budget — our estimate from vendor positioning, not a benchmark; budget models degrade first on long agentic chains.
Generated from the calculation above — every number traces to the sourced data; nothing here is written by an AI making things up.
Why DeepSeek V4 Flash scores 84%
How the $10.78/mo estimate is calculated
What could change this verdict
Cost risk
Official prices verified 2026-07-13; calculation is deterministic code over those prices.
At a glance
| Tool | Free tier | Paid entry | Verified |
|---|---|---|---|
| Anthropic Claude Opus 4.8 | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.5/M) — not modeled here | 2026-07-13 |
| Anthropic Claude Sonnet 5 | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.2/M) — not modeled here | 2026-07-13 |
| Anthropic Claude Haiku 4.5 | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.1/M) — not modeled here | 2026-07-13 |
| OpenAI GPT-5 | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.125/M) — not modeled here | 2026-07-13 |
| OpenAI GPT-5 Mini | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.025/M) — not modeled here | 2026-07-13 |
| OpenAI GPT-5 Nano | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.01/M) — not modeled here | 2026-07-13 |
| Google Gemini 2.5 Pro | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.125/M) — not modeled here | 2026-07-13 |
| Google Gemini 2.5 Flash | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.03/M) — not modeled here | 2026-07-13 |
| DeepSeek V4 Pro | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.0036/M) — not modeled here | 2026-07-13 |
| DeepSeek V4 Flash | No free tier | Pay-as-you-go — Prompt caching available (cached reads $0.0154/M) — not modeled here | 2026-07-13 |
Data sources
| Tool | Source | Verified |
|---|---|---|
| Anthropic Claude Opus 4.8 | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| Anthropic Claude Sonnet 5 | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| Anthropic Claude Haiku 4.5 | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| OpenAI GPT-5 | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| OpenAI GPT-5 Mini | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| OpenAI GPT-5 Nano | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| Google Gemini 2.5 Pro | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| Google Gemini 2.5 Flash | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| DeepSeek V4 Pro | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
| DeepSeek V4 Flash | OpenRouter live pricing (CalcSays daily sync, fetched 2026-07-13) | 2026-07-13 |
A monitor re-checks these pages for changes; when a vendor moves a price, the date updates and every verdict recomputes.
People also ask
What is the cheapest LLM API?
At publish time the floor among curated models is DeepSeek v4 Flash at $0.077/$0.154 per million tokens (open weights) — roughly 16–65× cheaper than flagship closed models. Whether it's cheap enough in QUALITY for your task is the real question; budget tiers degrade first on long agentic chains.
How much does the OpenAI API cost?
From live pricing (synced 2026-07-13): GPT-5 runs $1.25 in / $10 out per million tokens, GPT-5 mini $0.25/$2, GPT-5 nano $0.05/$0.40. Batch API halves these for non-realtime jobs. Set your volume above for the real monthly number.
How much does the Claude API cost?
From live pricing (synced 2026-07-13): Claude Sonnet 5 runs $2 in / $10 out per million tokens, Haiku 4.5 $1/$5, Opus 4.8 $5/$25. A feature doing 50M input + 10M output tokens a month costs $200 on Sonnet 5 — the calculator above prices your exact volume.