Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for togethercomputer

Together: Tev1 4B Experimental

togethercomputer/tev1-4b-experimental

Model weights
Compare

Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24 labeled options. It keeps Qwen's standard next-token head, so it is served through the regular chat completions API rather than a dedicated decisions runtime.

Send a system instruction followed by a JSON decision containing state, question, and options. The model returns a single option letter, which application code maps back to the option key. Recommended settings are temperature: 0, max_tokens: 8, and thinking disabled. It is intended for routing, classification, and policy checks, not generic chat. Together publishes the full data recipe and training code so teams can fine-tune their own variant.

Modalities
In / out price
$0.042 / $0per 1M
Context
33K
Released
Sep 30, 2026
Compare
PlaygroundProvidersPricingPerformanceUptimeAppsActivityDocumentationFAQExplore

Playground

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. It runs on the OpenRouter Decisions API rather than the OpenAI-compatible chat endpoint, so the request and response shapes below are specific to structured decisions — chat completions SDKs will not work with it.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Together: Tev1 4B Experimental on OpenRouter.

  • Decisions LabLab

Explore more models

Decision Model RankingsRanking
Latency
$0.042Free0.35s
98.33%
ProviderInput / Output /M
LatencyUptime
  • Favicon for Together
    Input $0.042 / Output Free
    Latency 0.35sUptime 98.33%
Latency
0.35s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
99.99%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.57%

Availability over the last 3 days

Last 72 hours
Availability 99.57%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.84%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for https://medquality-optimization.local/
medquality-decision-eval
new
66.5Mtokens
2.
Favicon for https://mstr-algo-hub.replit.app/worker-selling
MSTR worker-selling
new
42.8Mtokens
3.
Favicon for https://www.rawmodels.ai/
RawModels Fighting JEVs
new
16.9Mtokens
4.
Favicon for https://mstr-algo-hub.replit.app/worker-awareness
MSTR worker-awareness
new
14.4Mtokens
5.
Favicon for https://github.com/Beast-Industries/vyro-data-pipelines-python
clip-compliance-engine
new
10.1Mtokens
Rest of OpenRouter
28.2M
Top 5 Apps
2.13M

Frequently asked questions

Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24 labeled options. It keeps Qwen's standard next-token head, so it is served through the regular chat completions API rather than a dedicated decisions runtime.

The Tev1 4B Experimental documentation on OpenRouter includes the interactive Decisions Lab. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Tev1 4B Experimental costs $0.042/M input tokens and $0.00/M output tokens.

Tev1 4B Experimental has a 32,768 token context window. It supports up to 8 completion tokens.

Tev1 4B Experimental accepts text as input and returns structured decisions.

Tev1 4B Experimental was released on September 30, 2026.

More models from Together

StripedHyena Hessian 7B

This is the base model variant of the StripedHyena series, developed by Together.

StripedHyena uses a new architecture that competes with traditional Transformers, particularly in long-context data processing. It combines attention mechanisms with gated convolutions for improved speed, efficiency, and scaling. This model marks an advancement in AI architecture for sequence modeling tasks.

Text33K context
StripedHyena Nous 7B

This is the chat model variant of the StripedHyena series developed by Together in collaboration with Nous Research.

StripedHyena uses a new architecture that competes with traditional Transformers, particularly in long-context data processing. It combines attention mechanisms with gated convolutions for improved speed, efficiency, and scaling. This model marks a significant advancement in AI architecture for sequence modeling tasks.

Text33K context