For AI agents,
choose open models、
Understand the cost of every inference.

Tevos brings model selection, response speed and context costs together. Compare inference options and plan budgets for coding, conversations and long-running tasks.

THE MODEL LIBRARY

Choose the right open models
for your agents.

Input, cached input and output are priced separately. All model prices are in USD per million tokens.

Nemotron 3.5 Lightning 30B

open models
Input
$0.05
Cached input
$0.01
Output
$0.15
Pricing unit
USD / 1M tokens
View model prices

Qwen3.8 27B

open models
Input
$0.10
Cached input
$0.01
Output
$0.40
Pricing unit
USD / 1M tokens
View model prices

Ornith 1.5 35B

open models
Input
$0.10
Cached input
$0.01
Output
$0.40
Pricing unit
USD / 1M tokens
View model prices

GLM 5.3 Flash

open modelsLimited-time offer
Input
$0.08
Cached input
$0.02
Output
$0.33
Pricing unit
USD / 1M tokens
View model prices

DeepSeek V4.1 Flash

open modelsLimited-time offer
Input
$0.10
Cached input
$0.02
Output
$0.43
Pricing unit
USD / 1M tokens
View model prices
BUILT FOR AGENTS

Long context,
with clear cost boundaries.

From a single code completion to an ongoing agent, budget separately for new input, repeated context and output.

01 / INPUT

New tasks and input

Use the model's input price to estimate the cost of new prompts and task context.

02 / CACHED INPUT

Reusable context

Price cached input separately to budget for long conversations and repeated tool context.

03 / OUTPUT

Every model output

Plan the complete token budget for each task based on expected output length.

Coding Plan, from $10 per month

Explore plans in USD and choose models for your coding work.

View plans

Connect your coding tools

Understand each step, from model deployment to API requests.

Get started with the Tevos API
  1. Prepare a model deployment with Ready status
  2. Create an API key for that deployment
  3. Enter deployment details and send a model request
TevosModel API
Claude Code
Codex
OpenCode
Cline
Droid
Grok Build

Tool ecosystem illustration; compatibility is being verified. The API currently supports non-streaming chat requests. Full integration with the tools shown has not been verified.

CODING PLANS

Plan a monthly budget
for your coding agents.

From individual tasks to team collaboration, choose a plan for your usage. All amounts are shown in USD.

Starter

$10/ month

Reference monthly usage allowance
Approximately $12
5-hour limit
$1.11
Weekly limit
$2.77
Daily standby cost
$0.20
View plan

Pro

$29/ month

Reference monthly usage allowance
Approximately $35
5-hour limit
$3.23
Weekly limit
$8.08
Daily standby cost
$0.58
View plan

Team

$99/ month

Reference monthly usage allowance
Approximately $119
5-hour limit
$10.98
Weekly limit
$27.46
Daily standby cost
$1.98
View plan

Open models,
ready for your next agent task.

Contact us