Token TerminalControl room for AI in production
BenchmarksMarketProduction VolumeStatusAuditSLA HistoryFallback GeneratorBriefingsPricing
Sign in
Models tracked462
Providers63
Widest context2M · Auto Router (Beta)
Cheapest input$0.011 · DeepSeek: DeepSeek V4 Flash Latest
API uptime score60%

Intelligence

BenchmarksMarketProduction VolumeStatus

Pro tools

AuditSLA HistoryFallback GeneratorBriefings

Account

PricingAlertsCommunityHelp & feedbackSignup insights
System live

Run AI in production from a single control room.

Spend, incidents and failover for 450+ models and every host serving them — with the audit, the alert and the report that go with it.

Audit my AI spendPut incident alerts in Slack & PagerDutyBuild my failover plan

Public data, estimates, not investment advice.

tt-production --dashboard
Models tracked
462
Providers
63
API uptime
60%
Cheapest input
$0.011
Failover
ready
As of: Oct 1, 2026, 11:43 AM UTCSource: OpenRouter Models API and providers' public status feedsMethod: Catalog totals, prices and context are read from the current model feed. API uptime score is the percentage of reachable status feeds currently reporting operational; it is not an SLA.
ProviderModalitiesActions
OpenAI: GPT-6.1 Sol Pro
openai/gpt-6.1-sol-pro
OpenAI1.1M$2.00$10.00file · image · text1 day ago
Ad · OpenAI
OpenAI: GPT-6.1 Sol
openai/gpt-6.1-sol
OpenAI1.1M$2.00$10.00file · image · text1 day ago
Ad · OpenAI
Anthropic: Claude Sonnet 5.5
anthropic/claude-sonnet-5.5
Anthropic1M$2.00$10.00text · image · file2 days ago
Ad · Anthropic
Anthropic: Claude Sonnet 5.5 (batch)
anthropic/claude-sonnet-5.5:batch
Anthropic1M$1.00$5.00text · image · file2 days ago
Ad · Anthropic
TypeSafe: Jev Router
typesafe/jev-router
Typesafe1M$-1000000.000$-1000000.000audio · file · image · text · video5 days ago
Ad · OpenRouter
Perceptron: Perceptron Mk1.5
perceptron/perceptron-mk1.5
Perceptron37K$0.150$1.50text · image · video · audio5 days ago
Ad · OpenRouter
Fireworks: Ember-1
fireworks/ember-1
Fireworks1.0M$3.00$15.00text · image7 days ago
Ad · OpenRouter
Z.ai: GLM 5.3 Prime
z-ai/glm-5.3-prime
ZAi1M$2.80$8.80text7 days ago
Ad · OpenRouter
Qwen: Qwen3.8 Max Prime
qwen/qwen3.8-max-prime
Alibaba Qwen1M$4.00$12.00text · image · video7 days ago
Ad · OpenRouter
Space Bunny Alpha
stealth/space-bunny-alpha
Stealth1Mfreefreetext · image · video7 days ago
Ad · OpenRouter
  • OpenAI: GPT-6.1 Sol Pro
    OpenAI
    ctx 1.1Min $2.00out $10.001 day ago
    Ad · OpenAIAd · OpenRouter
  • OpenAI: GPT-6.1 Sol
    OpenAI
    ctx 1.1Min $2.00out $10.001 day ago
    Ad · OpenAIAd · OpenRouter
  • Anthropic: Claude Sonnet 5.5
    Anthropic
    ctx 1Min $2.00out $10.002 days ago
    Ad · AnthropicAd · OpenRouter
  • Anthropic: Claude Sonnet 5.5 (batch)
    Anthropic
    ctx 1Min $1.00out $5.002 days ago
    Ad · AnthropicAd · OpenRouter
  • TypeSafe: Jev Router
    Typesafe
    ctx 1Min $-1000000.000out $-1000000.0005 days ago
    Ad · OpenRouter
  • Perceptron: Perceptron Mk1.5
    Perceptron
    ctx 37Kin $0.150out $1.505 days ago
    Ad · OpenRouter
  • Fireworks: Ember-1
    Fireworks
    ctx 1.0Min $3.00out $15.007 days ago
    Ad · OpenRouter
  • Z.ai: GLM 5.3 Prime
    ZAi
    ctx 1Min $2.80out $8.807 days ago
    Ad · OpenRouter
  • Qwen: Qwen3.8 Max Prime
    Alibaba Qwen
    ctx 1Min $4.00out $12.007 days ago
    Ad · OpenRouterAd · Groq
  • Space Bunny Alpha
    Stealth
    ctx 1Min freeout free7 days ago
    Ad · OpenRouter
As of: Oct 1, 2026, 11:43 AM UTCSource: OpenRouter Models API Method: Prices are converted from per-token USD to USD per 1M tokens; context and release fields are displayed as published.

452 more models behind Pro

PRO

Free access covers the 10 most recent models. Pro unlocks the full sortable matrix, historical pricing trends, host-level latency and CSV/JSON exports.

Last 14 days · synced every 10 min

New Model Radar

Scanning the catalog…

Monthly cost & token calculator

Enter your monthly volume in millions of tokens to rank providers by real spend.

Advertising · outbound commercial links; we may receive compensation
  • Mistral: Mistral NemoMistral$1.25/mocheapest
    Ad · OpenRouter
  • inclusionAI: Ling 3.0 Flash VLInclusionai$1.67/mo+33%
    Ad · OpenRouter
  • inclusionAI: Ling 3.0 FlashInclusionai$1.68/mo+34%
    Ad · OpenRouter
  • OpenAI: gpt-oss-20bOpenAI$1.80/mo+44%
    Ad · OpenAI
  • IBM: Granite 4.0 MicroIbmGranite$1.97/mo+58%
    Ad · OpenRouter
  • Nex AGI: Nex-N2.5-MiniNexAgi$2.25/mo+80%
    Ad · OpenRouter
  • OpenAI: gpt-oss-20b (batch)OpenAI$2.32/mo+86%
    Ad · OpenAI
  • Sao10K: Llama 3 8B LunarisSao10k$2.50/mo+100%
    Ad · OpenRouter
As of: Oct 1, 2026, 11:43 AM UTCSource: OpenRouter Models API Method: Monthly estimate = entered input millions × published input price + entered output millions × published output price.
Token Terminal is the control room for teams running AI in production — spend, reliability, failover and reporting in one place. Each dataset states its date, source and method; estimates are labeled and are not investment advice. Updated continuously
Legal noticePrivacy policyTerms & conditionsData & methods
Help
Edit with