AI API Token Pricing Comparison
250 models across 19 providers, updated — compare input, output, and cached API prices in USD per million tokens.
| Try it | |||||||
|---|---|---|---|---|---|---|---|
GPT-6 Astra | OpenAI | High | 1.1M | $10.00 | $1.00 | $50.00 | Try API → |
GPT-6.1 Sol | OpenAI | High | 1.1M | $2.00 | $0.10 | $10.00 | Try API → |
GPT-6 Luna | OpenAI | Low | 1.1M | $0.10 | $0.01 | $0.50 | Try API → |
Claude Opus 5.5 | Anthropic | High | 1M | $4.00 | $0.20 | $20.00 | Try API → |
Claude Fable 5.1 | Anthropic | High | 1M | $10.00 | $0.25 | $50.00 | Try API → |
Claude Sonnet 5 | Anthropic | Mid | 1M | $2.00 | $0.20 | $10.00 | Try API → |
Gemini 4 Argon | High | 1M | $2.00 | $0.10 | $10.00 | Try in AI Studio → | |
Gemini 3.1 ProPreview | High | 1M | $2.00 | $0.20 | $12.00 | Try in AI Studio → | |
DeepSeek V4 Pro 0813DeepSeek | 3 providers | High | 1M | $0.66 | $0.022 | $1.98 | Try on Novita → |
GLM-5.2Z.ai | 3 providers | Mid | 1M | $1.40 | $0.26 | $4.40 | Try on Novita → |
Grok 4.7 | xAI | High | 500,000 | $2.00 | $0.50 | $6.00 | Try API → |
Llama 4 Maverick InstructMeta | 2 providers | High | - | $0.27 | - | $0.85 | Try on Novita → |
GPT-OSS Safeguard 20BPreviewOpenAI | Groq | High | - | $0.075 | - | $0.30 | Run on Vast → |
GPT-5.5 | OpenAI | High | 1.1M | $5.00 | $0.50 | $30.00 | Try API → |
GPT-5.5 Cyber | OpenAI | High | - | $12.50 | $1.25 | $75.00 | Try API → |
GPT-5.6 Cyber | OpenAI | High | 400,000 | $12.50 | $1.25 | $75.00 | Try API → |
GPT-5.4 Pro | OpenAI | High | 1.1M | $30.00 | - | $180.00 | Try API → |
GPT-5.5 Pro | OpenAI | High | 1.1M | $30.00 | - | $180.00 | Try API → |
o1-pro | OpenAI | High | - | $150.00 | - | $600.00 | Try API → |
GPT-5.6 Terra | OpenAI | Mid | 1.1M | $2.00 | $0.20 | $12.00 | Try API → |
GPT-5.4 | OpenAI | Mid | 1.1M | $2.50 | $0.25 | $15.00 | Try API → |
GPT-OSS 20BOpenAI | 2 providers | Low | - | $0.075 | $0.0375 | $0.30 | Run on Vast → |
GPT-OSS 120BOpenAI | 2 providers | Low | - | $0.15 | $0.075 | $0.60 | Run on Vast → |
GPT-5.4 nano | OpenAI | Low | 400,000 | $0.20 | $0.02 | $1.25 | Try API → |
GPT-5.4 mini | OpenAI | Low | 400,000 | $0.75 | $0.075 | $4.50 | Try API → |
Claude Mythos 5.1Preview | Anthropic | High | 1M | $10.00 | $0.25 | $50.00 | Try API → |
Claude Sonnet 5.5 | Anthropic | Mid | 1M | $2.00 | $0.10 | $10.00 | Try API → |
Claude Haiku 5.5 | Anthropic | Low | 1M | $0.10 | $0.01 | $0.50 | Try API → |
Gemini 2.5 Pro | High | 1M | $1.25 | $0.125 | $10.00 | Try in AI Studio → | |
Gemma 4 31B IT PearlGoogle | Together | Mid | - | $0.28 | - | $0.86 | Run on Vast → |
- GPT-6 Astra
- In
- $10.00
- Cached
- $1.00
- Out
- $50.00
- Try it
- Try API →
- GPT-6.1 Sol
- In
- $2.00
- Cached
- $0.10
- Out
- $10.00
- Try it
- Try API →
- GPT-6 Luna
- In
- $0.10
- Cached
- $0.01
- Out
- $0.50
- Try it
- Try API →
- Claude Opus 5.5
- In
- $4.00
- Cached
- $0.20
- Out
- $20.00
- Try it
- Try API →
- Claude Fable 5.1
- In
- $10.00
- Cached
- $0.25
- Out
- $50.00
- Try it
- Try API →
- Claude Sonnet 5
- In
- $2.00
- Cached
- $0.20
- Out
- $10.00
- Try it
- Try API →
- Gemini 4 Argon
- In
- $2.00
- Cached
- $0.10
- Out
- $10.00
- Try it
- Try in AI Studio →
- Gemini 3.1 ProPreview
- In
- $2.00
- Cached
- $0.20
- Out
- $12.00
- Try it
- Try in AI Studio →
- DeepSeek V4 Pro 0813· 3 hosts
- In
- $0.66
- Cached
- $0.022
- Out
- $1.98
- Try it
- Try on Novita →
- GLM-5.2· 3 hosts
- In
- $1.40
- Cached
- $0.26
- Out
- $4.40
- Try it
- Try on Novita →
- Grok 4.7
- In
- $2.00
- Cached
- $0.50
- Out
- $6.00
- Try it
- Try API →
- Llama 4 Maverick Instruct· 2 hosts
- In
- $0.27
- Cached
- -
- Out
- $0.85
- Try it
- Try on Novita →
- GPT-OSS Safeguard 20BPreview
- In
- $0.075
- Cached
- -
- Out
- $0.30
- Try it
- Run on Vast →
- GPT-5.5
- In
- $5.00
- Cached
- $0.50
- Out
- $30.00
- Try it
- Try API →
- GPT-5.5 Cyber
- In
- $12.50
- Cached
- $1.25
- Out
- $75.00
- Try it
- Try API →
- GPT-5.6 Cyber
- In
- $12.50
- Cached
- $1.25
- Out
- $75.00
- Try it
- Try API →
- GPT-5.4 Pro
- In
- $30.00
- Cached
- -
- Out
- $180.00
- Try it
- Try API →
- GPT-5.5 Pro
- In
- $30.00
- Cached
- -
- Out
- $180.00
- Try it
- Try API →
- o1-pro
- In
- $150.00
- Cached
- -
- Out
- $600.00
- Try it
- Try API →
- GPT-5.6 Terra
- In
- $2.00
- Cached
- $0.20
- Out
- $12.00
- Try it
- Try API →
- GPT-5.4
- In
- $2.50
- Cached
- $0.25
- Out
- $15.00
- Try it
- Try API →
- GPT-OSS 20B· 2 hosts
- In
- $0.075
- Cached
- $0.0375
- Out
- $0.30
- Try it
- Run on Vast →
- GPT-OSS 120B· 2 hosts
- In
- $0.15
- Cached
- $0.075
- Out
- $0.60
- Try it
- Run on Vast →
- GPT-5.4 nano
- In
- $0.20
- Cached
- $0.02
- Out
- $1.25
- Try it
- Try API →
- GPT-5.4 mini
- In
- $0.75
- Cached
- $0.075
- Out
- $4.50
- Try it
- Try API →
- Claude Mythos 5.1Preview
- In
- $10.00
- Cached
- $0.25
- Out
- $50.00
- Try it
- Try API →
- Claude Sonnet 5.5
- In
- $2.00
- Cached
- $0.10
- Out
- $10.00
- Try it
- Try API →
- Claude Haiku 5.5
- In
- $0.10
- Cached
- $0.01
- Out
- $0.50
- Try it
- Try API →
- Gemini 2.5 Pro
- In
- $1.25
- Cached
- $0.125
- Out
- $10.00
- Try it
- Try in AI Studio →
- Gemma 4 31B IT Pearl
- In
- $0.28
- Cached
- -
- Out
- $0.86
- Try it
- Run on Vast →
How we verify pricing data and normalize token costs.
Sponsored links may earn us a commission at no extra cost to you. Affiliate status never changes model ordering.
All product names, logos, and brands are property of their respective owners and are used for identification purposes only.
Showing featured models. Loading all models for search and filters…
Verified · GPT-6 Luna source · GPT-6.1 Sol source · Claude Sonnet 5.5 source · DeepSeek V4.1 Flash source · How we verify →
Compare pay-as-you-go API prices in USD per 1 million tokens, updated ; for monthly ChatGPT, Claude, Gemini, and Copilot plans, use subscription pricing, and verify rates directly before purchase because providers can change them without notice.
New decision-model route: TypeSafe Jev is $0.042 per million input tokens with free output on its direct System One API. It returns typed decisions rather than open-ended text; Opper gateway fees are separate.
New open-weight model: Aleph Alpha's Kolibri has downloadable Apache 2.0 weights, but no hosted input/output token rate is published in the checked official sources., so it is not shown as a misleading zero-cost row in this priced table or JSON feed.
Which AI API is cheapest right now? We track 250 models across 19 providers. The cheapest flagship is DeepSeek V3.2 at $0.27 per 1M input tokens; the absolute cheapest production model is Llama 3.1 8B Instruct at $0.02 per 1M input. The most expensive we track is o1-pro at $150.00 input / 600.00 output. Download the raw data as JSON.
Novita open-model API
One API for Llama, Qwen, DeepSeek and GLM — new accounts get $100 in sandbox credits for 90 days.
Affiliate disclosure: sponsored links may earn us a commission at no extra cost to you. Affiliate status never changes model ordering.
Qwen model family
Compare every current Qwen route
Separate Alibaba first-party aliases from managed Qwen hosts, with cache and long-context tiers.
Need exact math?
Use the token cost calculator
Enter your input/output token volume and estimate monthly spend before choosing a model.
Labs benchmark
Compare cost per correct answer
See which models turn token spend into correct reasoning, extraction, coding, and pricing answers.
Model pages
Open detailed model pricing
See per-model calculators, cached-token math, price history, and alternatives for high-demand models.
Subscription or API?
Compare monthly plans vs API usage
If you use AI through a chat app, calculate whether a subscription is cheaper than raw API tokens.
Frequently asked questions
Quick answers about API token pricing, freshness, and how to compare providers.
What does this AI API pricing comparison cover?
This page tracks pay-as-you-go API token pricing for 250 AI models across 19 providers — OpenAI, Anthropic, Google, DeepSeek, Mistral, xAI, Cohere, Groq, Together AI, Perplexity, and Meta Llama hosts. Each row shows input price, output price, cached-input price (where the provider offers prompt caching), and batch-discounted rates per million tokens. The data snapshot shown is from 2026-10-25.
How often is the pricing data updated?
The shared pipeline is scheduled every four hours; a successful run does not mean every model was re-verified. Use each row’s verification date and source, with confidence rules explained at /methodology/. The dataset snapshot is 2026-10-25, not a verification date for every price.
Which AI API is the cheapest right now?
As of 2026-10-25, the absolute cheapest production model we track is Llama 3.1 8B Instruct at $0.02 per million input tokens. The cheapest flagship-class model — meaning a top-tier model from a major lab, not a small or distilled variant — is DeepSeek V3.2 at $0.27 per million input tokens. The most expensive model we track is o1-pro at $150.00 input / 600.00 output per 1M tokens.
How do I compare two specific AI providers like OpenAI and Anthropic?
Use the table search and filter controls above to narrow to a single provider, then sort by input or output price. For deeper provider-level pages with FAQs, methodology, and historical pricing, see /openai-pricing/, /anthropic-pricing/, /google-ai-pricing/, /deepseek-pricing/, /mistral-ai-pricing/, /cohere-pricing/, or any other provider listed. For workload-level math, the token cost calculator at /calculators/token-cost/ runs your input/output volume against every model side-by-side.
Should I pay per token via API or subscribe to ChatGPT Plus or Claude Pro?
Choose a subscription for interactive work in its app, and API access for programmatic workloads. Compare the full plan fee against your expected input, output and tool charges rather than assuming a subscription includes API access. The /subscription-vs-api/ tool estimates the break-even point for your volume.
