Provider key onboarding probe

Together AI | commercial launch readiness

Together AI commercial launch readiness decides whether a key can move from identification into inventory, pricing, routing, and launch. TestKey starts with 1 covered models, global route, sample models meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo, then verifies with read-only probes.

Provider

Together AI

global route

Model coverage

1

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

Probe dimension

commercial launch readiness

commercial-launch

Onboarding signal

global route, check region/IP, balance, pricing, and stability first

together

Read-only probes

1

current_key

Sample metrics

8

key_valid / requests_total / runtime_model / runtime_model_allowed

Ten capabilities

5

operational actions / model permission matrix / limit matrix

Provider onboarding summary

Provider

Together AI

Probe dimension

commercial-launch

Model coverage

1

Read-only check. Detection data burns after 5 minutes.

Why this probe matters

Together AI commercial launch readiness decides whether a key can move from identification into inventory, pricing, routing, and launch. TestKey starts with 1 covered models, global route, sample models meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo, then verifies with read-only probes.

Provider: Together AI
Model coverage: 1
Probe dimension: commercial launch readiness

How to prove it

Read-only check. Detection data burns after 5 minutes.

Identify the real provider first, then verify commercial launch readiness; do not treat OpenAI-compatible as real OpenAI by default.
Use 1 covered models as candidates, then read /models, balance, error bodies, and limit headers.
global route, check region/IP, balance, pricing, and stability first

Next action

Together AI commercial launch readiness should become an action: add provider config, fill pricing, import inventory, set route, add monitoring, or send to human review.

Read-only check. Detection data burns after 5 minutes.
Onboarding signal: global route, check region/IP, balance, pricing, and stability first
Model coverage: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

Ten key capability anchors

Together AI has 1 read-only account probes configured, currently supporting operational actions / model permission matrix / limit matrix / key identity / capability matrix. These anchors feed the real TestKey detection path, not just admin display.

Read-only probes: current_key, used to prove provider identity, models, balance, or subscription state.
Sampleable metrics: key_valid / requests_total / runtime_model / runtime_model_allowed / tokens_limit / token_type / token_role / token_scopes.
Ten-capability anchors: operational actions / model permission matrix / limit matrix / key identity / capability matrix.

Open key checker

Read-only check. Detection data burns after 5 minutes.

Open providers

Together AI

Open models

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo