Highflame Identity is now open source: agent identity on open standards. View on GitHub
▸ CONTROL · MODEL GATEWAY

Give agents model access. Control spend by agent.

Connect agents to 150+ model providers through one gateway. Protect provider credentials, inspect prompts for sensitive data, enforce usage policies, and track costs by agent, person, and team. Set budgets to keep spending under control.

Works with 150+ model providers, OpenAI, Anthropic, LiteLLM, Portkey
SOC 2 Type II, GDPR, HIPAA
The problem

Shared keys hide who's spending what.

As teams connect AI agents to more models, provider keys spread across scripts, applications, and developer environments. Multiple agents often share the same credentials, making it difficult to trace usage, control spending, or protect sensitive information sent to models.

Keys spread everywhere

keys everywhere

Provider credentials end up in scripts, repositories, and agent configurations, increasing exposure and making access difficult to manage.

Spending without accountability

cost per key

Shared API keys make it difficult to attribute model usage and cost to individual agents, people, or teams.

Uncontrolled model usage

runaway requests

Agents can generate thousands of requests automatically, consuming tokens and exceeding budgets before anyone notices.

What you get

Give teams model choice without losing control.

Secure model access without shared keys

Keep provider credentials in a secure vault while agents authenticate through Highflame. Give teams access to approved models without distributing provider API keys.

Provider credentialsvault
  • OpenAI · productionIn vault
  • Anthropic · productionWIF
  • support-botCompany SSO

Resolved per request and kept at the gateway

Protect sensitive information

Inspect model requests for secrets and personal information. Apply configured redaction policies before sending requests to providers, with prompt and response storage optional.

Prompt to modelmasked

Refund order 8812 for jane@acme.com, card 4111 1111 …

Refund order 8812 for [EMAIL], card [CARD]

Stored: metadata only (model, tokens, cost, latency)

Track and control spending

Attribute model calls, token usage, and costs to agents, people, projects, and teams. Set budgets and usage limits to prevent additional calls once configured limits are reached.

Team · Supportbudget
$2,000 of $2,000Limit reached

Further calls stopped until the budget resets

Keep model access reliable

Route requests across supported providers and configure failover when a model becomes unavailable. Change routing without modifying individual agents, and integrate with existing LiteLLM or Portkey deployments.

Routing · support-botauto
  • OpenAIOutage
  • AnthropicServing traffic

Traffic moved automatically, with no code change

Cost controls

Set budgets that agents can't ignore.

AI agents can generate model requests at machine speed. Highflame applies spending limits as part of its authorization process, helping teams control costs before additional requests are sent.

Model Gateway/Spend
Last 14 days
Total spend$15.4K+12% vs prior 14 days
Model calls1.2Macross 150+ providers
Tokens2.1B1.7B input · 0.4B output
Budgets at limit1further calls stopped
Daily spend by agent
  • support-bot
  • report-bot
  • research-agent
  • Other
$0 $500 $1,000 $1,500 Oct 21 · support-bot: $331 Oct 21 · report-bot: $209 Oct 21 · research-agent: $148 Oct 21 · Other: $183 Oct 22 · support-bot: $444 Oct 22 · report-bot: $281 Oct 22 · research-agent: $199 Oct 22 · Other: $245 Oct 23 · support-bot: $469 Oct 23 · report-bot: $296 Oct 23 · research-agent: $210 Oct 23 · Other: $259 Oct 24 · support-bot: $469 Oct 24 · report-bot: $296 Oct 24 · research-agent: $210 Oct 24 · Other: $259 Oct 25 · support-bot: $456 Oct 25 · report-bot: $288 Oct 25 · research-agent: $204 Oct 25 · Other: $252 Oct 26 · support-bot: $309 Oct 26 · report-bot: $195 Oct 26 · research-agent: $138 Oct 26 · Other: $171 Oct 27 · support-bot: $279 Oct 27 · report-bot: $176 Oct 27 · research-agent: $125 Oct 27 · Other: $154 Oct 28 · support-bot: $375 Oct 28 · report-bot: $237 Oct 28 · research-agent: $168 Oct 28 · Other: $207 Oct 29 · support-bot: $502 Oct 29 · report-bot: $317 Oct 29 · research-agent: $224 Oct 29 · Other: $277 Oct 30 · support-bot: $529 Oct 30 · report-bot: $334 Oct 30 · research-agent: $237 Oct 30 · Other: $292 Oct 31 · support-bot: $528 Oct 31 · report-bot: $333 Oct 31 · research-agent: $236 Oct 31 · Other: $292 Nov 1 · support-bot: $512 Nov 1 · report-bot: $323 Nov 1 · research-agent: $229 Nov 1 · Other: $283 Nov 2 · support-bot: $347 Nov 2 · report-bot: $219 Nov 2 · research-agent: $155 Nov 2 · Other: $192 Nov 3 · support-bot: $312 Nov 3 · report-bot: $197 Nov 3 · research-agent: $139 Nov 3 · Other: $172 Oct 21Oct 23Oct 25Oct 27Oct 29Oct 31Nov 2
AgentSpendShareBudget
support-bot $5,860 38% 88% used
report-bot $3,701 24% 89% used
research-agent $2,621 17% Limit reached
Other $3,238 21% 65% used
Daily spend by team
  • Support
  • Finance
  • Engineering
  • Other
$0 $500 $1,000 $1,500 Oct 21 · Support: $357 Oct 21 · Finance: $235 Oct 21 · Engineering: $174 Oct 21 · Other: $105 Oct 22 · Support: $479 Oct 22 · Finance: $316 Oct 22 · Engineering: $234 Oct 22 · Other: $140 Oct 23 · Support: $506 Oct 23 · Finance: $333 Oct 23 · Engineering: $247 Oct 23 · Other: $148 Oct 24 · Support: $506 Oct 24 · Finance: $333 Oct 24 · Engineering: $247 Oct 24 · Other: $148 Oct 25 · Support: $492 Oct 25 · Finance: $324 Oct 25 · Engineering: $240 Oct 25 · Other: $144 Oct 26 · Support: $334 Oct 26 · Finance: $220 Oct 26 · Engineering: $163 Oct 26 · Other: $98 Oct 27 · Support: $301 Oct 27 · Finance: $198 Oct 27 · Engineering: $147 Oct 27 · Other: $88 Oct 28 · Support: $404 Oct 28 · Finance: $266 Oct 28 · Engineering: $197 Oct 28 · Other: $118 Oct 29 · Support: $541 Oct 29 · Finance: $356 Oct 29 · Engineering: $264 Oct 29 · Other: $158 Oct 30 · Support: $571 Oct 30 · Finance: $376 Oct 30 · Engineering: $278 Oct 30 · Other: $167 Oct 31 · Support: $569 Oct 31 · Finance: $375 Oct 31 · Engineering: $278 Oct 31 · Other: $167 Nov 1 · Support: $552 Nov 1 · Finance: $364 Nov 1 · Engineering: $269 Nov 1 · Other: $162 Nov 2 · Support: $374 Nov 2 · Finance: $246 Nov 2 · Engineering: $182 Nov 2 · Other: $109 Nov 3 · Support: $336 Nov 3 · Finance: $221 Nov 3 · Engineering: $164 Nov 3 · Other: $98 Oct 21Oct 23Oct 25Oct 27Oct 29Oct 31Nov 2
TeamSpendShareBudget
Support $6,322 41% 84% used
Finance $4,163 27% Limit reached
Engineering $3,084 20% 62% used
Other $1,850 12% 52% used
Daily spend by model
  • claude-sonnet
  • gpt-4.1
  • gemini-2.5-pro
  • Other
$0 $500 $1,000 $1,500 Oct 21 · claude-sonnet: $383 Oct 21 · gpt-4.1: $270 Oct 21 · gemini-2.5-pro: $131 Oct 21 · Other: $87 Oct 22 · claude-sonnet: $514 Oct 22 · gpt-4.1: $362 Oct 22 · gemini-2.5-pro: $175 Oct 22 · Other: $117 Oct 23 · claude-sonnet: $543 Oct 23 · gpt-4.1: $383 Oct 23 · gemini-2.5-pro: $185 Oct 23 · Other: $123 Oct 24 · claude-sonnet: $543 Oct 24 · gpt-4.1: $383 Oct 24 · gemini-2.5-pro: $185 Oct 24 · Other: $123 Oct 25 · claude-sonnet: $528 Oct 25 · gpt-4.1: $372 Oct 25 · gemini-2.5-pro: $180 Oct 25 · Other: $120 Oct 26 · claude-sonnet: $358 Oct 26 · gpt-4.1: $252 Oct 26 · gemini-2.5-pro: $122 Oct 26 · Other: $81 Oct 27 · claude-sonnet: $323 Oct 27 · gpt-4.1: $227 Oct 27 · gemini-2.5-pro: $110 Oct 27 · Other: $73 Oct 28 · claude-sonnet: $434 Oct 28 · gpt-4.1: $306 Oct 28 · gemini-2.5-pro: $148 Oct 28 · Other: $99 Oct 29 · claude-sonnet: $581 Oct 29 · gpt-4.1: $409 Oct 29 · gemini-2.5-pro: $198 Oct 29 · Other: $132 Oct 30 · claude-sonnet: $612 Oct 30 · gpt-4.1: $432 Oct 30 · gemini-2.5-pro: $209 Oct 30 · Other: $139 Oct 31 · claude-sonnet: $611 Oct 31 · gpt-4.1: $431 Oct 31 · gemini-2.5-pro: $208 Oct 31 · Other: $139 Nov 1 · claude-sonnet: $593 Nov 1 · gpt-4.1: $418 Nov 1 · gemini-2.5-pro: $202 Nov 1 · Other: $135 Nov 2 · claude-sonnet: $401 Nov 2 · gpt-4.1: $283 Nov 2 · gemini-2.5-pro: $137 Nov 2 · Other: $91 Nov 3 · claude-sonnet: $361 Nov 3 · gpt-4.1: $254 Nov 3 · gemini-2.5-pro: $123 Nov 3 · Other: $82 Oct 21Oct 23Oct 25Oct 27Oct 29Oct 31Nov 2
ModelSpendShareBudget
claude-sonnet $6,785 44% 81% used
gpt-4.1 $4,780 31% 82% used
gemini-2.5-pro $2,313 15% Limit reached
Other $1,542 10% 58% used
Set limits by agent, person, or team
Define dollar budgets, token limits, and usage quotas that match how your organization manages model access.
Know where every dollar goes
View spending, token consumption, and model calls by agent, person, project, team, or provider.
Stop runaway usage
When a configured budget or quota is reached, the gateway blocks additional requests subject to that limit.
For the teams rolling agents out

More models. Less operational overhead.

Centralize provider credentials, model routing, and usage policies without requiring every development team to manage them independently.

Keep existing model proxies where appropriate, while Highflame adds identity-aware security and authorization controls.

Provider keys

✕Before

Personal API keys live in scripts, repos and laptops.

✓With Highflame

Keys stay in a vault and are resolved per request. People sign in with company SSO.

Runaway spend

✕Before

A looping agent runs up thousands of dollars before anyone notices.

✓With Highflame

A budget per team, person or agent stops further calls the moment it's reached.

Switching models

✕Before

Moving a team to a different model means code changes in every agent.

✓With Highflame

Admins re-route a team or agent to another model, with no code changes.

How it works

Every model call secured and accounted for.

StepWhat happens
1 · AuthenticateVerify the agent's identity and keep downstream model-provider credentials at the gateway.
2 · InspectCheck model requests for security risks and sensitive information, applying configured redaction policies.
3 · AuthorizeEvaluate the request against identity, security policies, budgets, and usage limits before forwarding it.
4 · RouteSend approved requests to the selected model provider, with configured failover options when needed.
5 · RecordCapture model usage, token consumption, latency, cost, and authorization decisions, attributed to the agent and its associated person or project.

Every call through the gateway carries the agent's own identity from Highflame Identity, built on the open-source ZeroID core, so each decision knows which agent acted and for whom. See how agents get their identity.

▸ PRODUCTION READY
150+
model providers through one gateway
Per agent
dollar budgets and token limits, plus per team and person
Metadata only
by default; prompts and responses stored only if you opt in
< 50 ms
added to each model call

Frequently asked questions

Something else on your mind? Talk to our team.

01What is an LLM gateway for agents?

A single point that every agent's model calls pass through, where the agent is identified, the prompt is inspected, the call is decided by policy, and usage and cost are recorded. Highflame's Model Gateway adds budgets, token limits and automatic failover across 150+ model providers.

02Can it sit behind LiteLLM or Portkey?

Yes. Highflame plugs into the proxy or gateway you already run and makes the policy decision, or it can serve as the gateway itself.

03How is cost tracked?

Each call records its input and output tokens and cost against the agent that made it and the person it works for. You can see cost, share of spend and call counts by project, agent, person and model, and export it by team or department for chargeback.

04Can we set budgets and token limits?

Yes. Set dollar budgets per team, person or agent, and token limits per person, agent or model. When a limit is reached, further calls stop.

05Does it work across model providers?

Yes. More than 150 model providers sit behind one gateway, with the same policy and credential setup for each. If a provider goes down, traffic fails over automatically, and admins can re-route a team or agent to another model without code changes.

06Does Highflame store our prompts?

No. By default Highflame records only metadata such as the model, tokens, cost and latency. Prompts and responses are stored only if you turn that on.

Deploy your way
  • Managed SaaSHosted and run by Highflame
  • Your private cloudDeployed in your VPC
  • On-premSelf-hosted in your environment
SOC 2 Type II · GDPR · HIPAA
DISCOVERY · IDENTITY · CONTROL · GOVERNANCE

Know who's using your models. Control what they spend.

See how Highflame secures model access, tracks usage by agent, and enforces spending policies across your AI environment.