Perplexity
Perplexity: Decider 27B Latest
This model always redirects to the latest model in the Decider 27B family.
Input$0.021per 1M
Output$0.00per 1M
Context262.1K
Max output235,929
Marketplace
Showing 12 of 656 modelsAI Model Marketplace
Search, filter, compare, and audit live model pricing with TVP buyer pricing.
656Models88ProvidersLivePricing
Select up to 3 live models to compare pricing, context, and endpoint coverage.
nace-ai
Nace.AI: Drex v2.0
Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI, the larger successor to [Drex v1.5](TVP catalog). Given a state (text or JSON) and typed questions (yes/no, multiple choice,...
Input$0.063per 1M
Output$0.00per 1M
Context131.1K
Max output117,964
meta
Meta: Muse Wonder
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
Input$4.20per 1M
Output$21.00per 1M
Context1M
Max output943,718
Microsoft
Microsoft: Microsoft-Decision-1
Microsoft-Decision-1 is a small model built for fast decision-making. Instead of generating text, it reads the provided content and returns a calibrated probability for each fixed answer option, so the...
Input$0.0441per 1M
Output$0.00per 1M
Context32.8K
Max output29,491
nace-ai
Nace.AI: Drex v1.5
Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for...
Input$0.042per 1M
Output$0.00per 1M
Context131.1K
Max output117,964
cloudflare
Cloudflare: Clef Omni
Clef Omni is the mixture-of-experts member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active parameters) served on Workers AI. It turns a state...
Input$0.1575per 1M
Output$0.00per 1M
Context65.5K
Max output58,982
StepFun
StepFun: Step 5 Preview
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
Input$1.05per 1M
Output$2.84per 1M
Context1M
Max output64,000
Upstage
Upstage: Solar Decide Flash
Solar Decide Flash is Upstage's low-latency structured decision model, a faster variant of [Solar Decide](/upstage/solar-decide) built on Solar Mini 4 and served through the System One (`/v1/systemone`) API. Instead of...
Input$0.0525per 1M
Output$0.00per 1M
Context524.3K
Max output471,859
Anthropic
Anthropic: Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Input$0.105per 1M
Output$0.525per 1M
Context1M
Max output128,000
Anthropic
Anthropic: Claude Haiku 5.5 (batch)
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Input$0.0525per 1M
Output$0.2625per 1M
Context1M
Max output128,000
Perplexity
Perplexity: Decider V1.1 27B
Decider V1.1 27B is a new checkpoint of Perplexity's decision model, succeeding [Decider V1 27B](/perplexity/pplx-decider-v1-27b) with the same API contract. Instead of generating text, it reads content passed as `state`...
Input$0.021per 1M
Output$0.00per 1M
Context262.1K
Max output235,929
elevenlabs
ElevenLabs: Eleven v4
Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character...
Input$42.00per 1M
Output$0.00per 1M
Context0
Max output0
Showing 12 of 656 models
Internal distribution
Use the marketplace with guide and comparison pages
These internal routes help buyers move from generic catalog browsing into comparison and buying-intent pages.
Popular guides
Buyer-intent traffic pages
Best AI models for coding, debugging, and code reviewCompare live coding LLMs by reasoning support, tool calling, context window size, and token pricing before you choose a model for engineering work.Cheapest AI models for production trafficFind the lowest-cost live AI models on TVP using current token pricing, context size, and capabilities so you can reduce serving cost without guessing.Best long-context AI models for large documents and repositoriesCompare live long-context AI models by context window, pricing, and capability support for document analysis, repo review, transcripts, and large prompts.Best reasoning models for complex analysis and decision supportCompare live reasoning-capable AI models by context, pricing, and capability support for research, planning, analysis, and multi-step tasks.
Comparison pages
Head-to-head decision routes
GPT-5.6 Luna vs Grok 4.20Compare GPT-5.6 Luna vs Grok 4.20 using live TVP pricing, context windows, tool support, and capability data before choosing a production route.GPT-5.6 Luna vs Claude Sonnet 5Compare GPT-5.6 Luna vs Claude Sonnet 5 with live pricing, context, and capability signals to choose a stronger fit for writing, analysis, or agent workflows.GPT-5.4 vs Claude Sonnet 5Compare GPT-5.4 vs Claude Sonnet 5 by live TVP pricing, context, and capability support for high-stakes analytical, writing, and agent workloads.Grok 4.20 vs Gemini 2.5 ProCompare Grok 4.20 vs Gemini 2.5 Pro using live TVP catalog data for context, pricing, and capabilities across research, multimodal, and agent workflows.
Provider matchups
Route strategy pages
OpenAI vs Anthropic AI modelsCompare live OpenAI and Anthropic model coverage, context windows, capabilities, and token pricing on TVP before choosing a production provider route.OpenAI vs Google AI modelsCompare live OpenAI and Google AI model coverage, context size, capabilities, and token pricing before routing production traffic between the two providers.Anthropic vs Google AI modelsCompare live Anthropic and Google model coverage, context windows, capabilities, and pricing on TVP for writing, research, multimodal, and agent workflows.
Curated from live data
Recommended starting points
Shortlist useful models before drilling into the full marketplace.
SpaceXAI: Grok 4.20
Strong fit for complex work with reasoning support and large context.
xAI2M context
Input$1.31per 1M
Output$2.63per 1M
Mistral: Mistral Nemo
Lowest combined TVP input and output price among paid text models.
Mistral AI131.1K context
Input$0.0305per 1M
Output$0.0315per 1M
TypeSafe: Jev Router
Image-capable model selected from live pricing and capability data.
Inputn/aper 1M
Outputn/aper 1M
SpaceXAI: Grok 4.20 Multi-Agent
Largest context window with numeric input and output pricing.
xAI2M context
Input$1.31per 1M
Output$2.63per 1M
How TVP pricing works
Transparent pricing buyers can audit
Simple pricing rules, live source data, and exact decimals remain visible for review.
Provider pricing syncs live
TVP reads current provider catalog data and refreshes on demand.
TVP price is shown for planning
Buyers can compare options using one consistent TVP pricing view.
Prices are shown per 1M tokens
Tiny token decimals are normalized into buyer-readable rates.
Exact decimals stay available
Detailed pricing fields remain visible for audit and billing checks.
Last synced: 10/12/2026, 8:04:27 PM
