Decision API pricing compared: OpenAI, Jev, Clef and more
Decision APIs answer yes/no, choice and score questions with probabilities and bill input tokens only. Hosted list prices run from $0.01 per 1M input tokens (Perplexity pplx-decider-flash) to $0.24 (Cloudflare Clef); the OpenAI Decisions API is $0.10, and Jev and Microsoft-Decision-1 are $0.042. Each price links to the vendor page with the date we checked it. Looking for free tools instead? See free APIs and MCP servers for AI agents.
Featured
Verified & partly verifiedNewBetaVerified
OpenRouter Armor
OpenRouter · Guardrail / tool-call policy
Armor evaluation is not billed during the beta. OpenRouter says pricing will be announced before general availability. Normal model inference is still billed.
View details
Verified
OpenAI Decisions API
OpenAI · Decision model
$0.10 per 1M uncached input tokens; output tokens not charged.
View details
BetaVerified
Microsoft-Decision-1
Microsoft (Foundry) · Decision model
$0.042 per 1M input tokens; output $0 (OpenRouter listing, provider Azure). Vercel AI Gateway lists the same $0.042.
View details
Verified
Vercel AI Gateway — Decisions endpoint
Vercel · Gateway / proxy
No markup and no platform fee on tokens: you pay the provider’s list price (also with your own key). Per-request cost is reported in response metadata; the docs’ example shows $0.10 per 1M for openai/gpt-6-luna-decisions, matching OpenAI’s list price.
View details
Partly verified
Jev (TypeSafe AI)
TypeSafe AI · Decision model
$0.042 per 1M input tokens ($42 per billion) for both Jev 1.14 and 1.13; output tokens free. Long-context mode costs the same per token. OpenRouter and Vercel AI Gateway list the same $0.042.
View details
Verified
Cloudflare Clef (Clef, Clef-flash, Clef-omni)
Cloudflare (Workers AI) · Decision model
Clef $0.240, Clef-omni $0.150, Clef-flash $0.038 per 1M input tokens; no output-token charge. Media are converted to input tokens.
View details
All APIs
20 morePerplexity Decisions API (pplx-decider)
$0.02 per 1M input tokens on pplx-decider-v1.2 and $0.01 on pplx-decider-flash-v1.2; output tokens free; no per-request fee. State, questions, and images count as input. In Perplexity’s tests an image cost about 1,000 input tokens per megapixel.
NewVerified
Inception Mercury Decide
Input listed as $0.04 → $0.02 per 1M tokens (shown as a 50%-off promotion); cached input and output $0.
Verified
Liquid AI d1
$0.02 per 1M input tokens (cached input also $0.02), $0 output, for d1 on Liquid’s pricing page. New orgs get $2 free credit on Liquid Console.
Partly verified
Strands Decider 2B (open source)
Free open weights (Apache-2.0); you pay your own compute.
Verified
AWS Bedrock Guardrails
Content filters (text) $0.15 per 1,000 text units; denied topics $0.15/1k; sensitive-info filters $0.10/1k; regex and word filters free; contextual grounding $0.10/1k; Automated Reasoning checks $0.17/1k per policy; image content filter $0.00075/image. A text unit is up to 1,000 characters.
Verified
Content Safety in Foundry Control Plane (formerly Azure AI Content Safety)
Free (F0) tier: 5,000 text records/month and 5,000 images/month; usage stops at the limit. A text record is up to 1,000 characters.
Verified
Gemini structured output (Vertex AI / Agent Platform)
Per-token Gemini pricing; for example Gemini 3.8 Flash is $0.75 / $3.75 per 1M input/output tokens (introductory, through 2026-12-31), then $1.50 / $7.50 from 2027-01-01 (non-global endpoints cost 10% more). The response schema counts toward the input token limit.
Verified
Anthropic Claude (tool use / structured outputs)
Per 1M input/output tokens: Haiku 5.5 $0.10/$0.50 (prompts up to 100k); Haiku 4.5 $1/$5; Sonnet 5.5 $2/$10; Opus 5.5 $4/$20; Claude Fable 5.1 (Anthropic’s top model for demanding reasoning) $10/$50. US-only inference_geo costs 1.1x; Batch is 50% off. Anthropic says structured outputs work on every model.
Verified
OpenAI Moderation (omni-moderation)
Free.
Verified
Cohere Classify
No Classify price found. cohere.com/pricing does not list Classify (it lists Model Vault instances and legacy Command/Aya token prices). Trial keys are free but rate limited and not for production.
Verified
Laya (open source)
Free open weights (Apache-2.0); you pay your own compute.
Verified
llama.cpp decision endpoint (/v1/systemone)
Free and open source; you pay your own compute. Check each model’s license (OpenJev is CC BY-NC 4.0, non-commercial).
Verified
DeepSeek Search & Fetch API
Search $0.75 and Fetch $0.75 per 1,000 successful requests. Only HTTP 200 responses with a result are billed: empty searches, failed fetches and timeouts are free, and count does not change the price. Charges come out of your topped-up or granted balance.
NewVerified
Liquid AI d1-ultra
$0.042 per 1M input tokens, cached input $0.042, output $0. Liquid says the price is the same on Liquid Console, OpenRouter and Vercel AI Gateway; new Liquid Console organizations get $2 free credit.
NewVerified
H2O-Lightning-4B (open source)
Free open weights (Apache-2.0); you pay your own GPU. Each decision is one forward pass and one output token, so cost is input tokens only. The $0.021 per 1,000 decisions estimate we quoted on Oct 16 is no longer on the model card.
Partly verified
LLM Gateway — Decisions
Jev 1.13: $0.042 per 1M input tokens, output free. Prices for the other decision models on the gateway were not checked.
Verified
Articul8 Bivia
$0.042 per 1M input tokens, $0 output tokens.
NewBetaVerified
Mistral Responses API
No separate Responses price: you pay the model’s API token price. Example: mistral-large-4 $0.70 per 1M input, $0.07 cached input, $2.10 output.
NewBetaVerified
Cartesia Managed Agents
Voice agents at a standard $0.03 a minute, paid from prepaid agent dollars: Free plan $1/month (about 33 minutes), Startup $49/month, Scale $299/month includes $299 for agents. Enterprise custom.
NewBetaPartly verified
Phonic-1 (speech-to-speech)
Starter $0.07/min, no minimum. Pro $0.065/min with a $200 monthly minimum (about 3,100 minutes). Enterprise custom. No LLM pass-through or per-token charges.
NewBetaPartly verified