Compare Keyvera rates across the live catalog. Every token price below is normalized to USD per one million tokens, so the true cost of input, output, and cached context is easy to see.
Keyvera publishes model-level input, output, cache-write, and cache-read pricing. The comparison uses the rates supplied by the public Keyvera Model Plaza and labels the billing unit directly.
Use this pricing page to estimate production AI API costs before traffic scales. Input and output rates matter for every request, while cache-read and cache-write rates are important for repeated context, assistants, retrieval workflows, and long-running agents.
Some models appear in multiple access groups. Use the filters to find the route that matches your workflow and compare its exact published token rates.
| Model / access group | Input | Output | Cache read | Compared with official input |
|---|---|---|---|---|
claude-fable-5Claude Code · Anthropic | $5.00/ 1M tokens | $25.00/ 1M tokens | $0.50/ 1M tokens | SAVE 50%Official $10.00 |
claude-haiku-4-5Claude Code · Anthropic | $0.50/ 1M tokens | $2.50/ 1M tokens | $0.05/ 1M tokens | SAVE 50%Official $1.00 |
claude-opus-4-6Claude Code · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-7Claude Code · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-8Claude Code · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-sonnet-4-6Claude Code · Anthropic | $1.50/ 1M tokens | $7.50/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $3.00 |
claude-sonnet-5Claude Code · Anthropic | $1.00/ 1M tokens | $5.00/ 1M tokens | $0.10/ 1M tokens | SAVE 50%Official $2.00 |
claude-fable-5Claude Max · Anthropic | $5.00/ 1M tokens | $25.00/ 1M tokens | $0.50/ 1M tokens | SAVE 50%Official $10.00 |
claude-haiku-4-5Claude Max · Anthropic | $0.50/ 1M tokens | $2.50/ 1M tokens | $0.05/ 1M tokens | SAVE 50%Official $1.00 |
claude-opus-4-6Claude Max · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-7Claude Max · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-8Claude Max · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-sonnet-4-6Claude Max · Anthropic | $1.50/ 1M tokens | $7.50/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $3.00 |
claude-sonnet-5Claude Max · Anthropic | $1.00/ 1M tokens | $5.00/ 1M tokens | $0.10/ 1M tokens | SAVE 50%Official $2.00 |
claude-fable-5Claude Plus · Anthropic | $5.00/ 1M tokens | $25.00/ 1M tokens | $0.50/ 1M tokens | SAVE 50%Official $10.00 |
claude-haiku-4-5Claude Plus · Anthropic | $0.50/ 1M tokens | $2.50/ 1M tokens | $0.05/ 1M tokens | SAVE 50%Official $1.00 |
claude-opus-4-6Claude Plus · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-7Claude Plus · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-8Claude Plus · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-sonnet-4-6Claude Plus · Anthropic | $1.50/ 1M tokens | $7.50/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $3.00 |
claude-sonnet-5Claude Plus · Anthropic | $1.00/ 1M tokens | $5.00/ 1M tokens | $0.10/ 1M tokens | SAVE 50%Official $2.00 |
gpt-5.4Codex Pro · OpenAI-compatible | $1.25/ 1M tokens | $7.50/ 1M tokens | $0.13/ 1M tokens | SAVE 50%Official $2.50 |
gpt-5.4-miniCodex Pro · OpenAI-compatible | $0.38/ 1M tokens | $2.25/ 1M tokens | $0.04/ 1M tokens | SAVE 49%Official $0.75 |
gpt-5.5Codex Pro · OpenAI-compatible | $2.50/ 1M tokens | $15.00/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
gpt-5.6-lunaCodex Pro · OpenAI-compatible | $0.50/ 1M tokens | $3.00/ 1M tokens | $0.05/ 1M tokens | SAVE 0%Official $0.20 |
gpt-5.6-solCodex Pro · OpenAI-compatible | $2.50/ 1M tokens | $15.00/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
gpt-5.6-terraCodex Pro · OpenAI-compatible | $1.25/ 1M tokens | $7.50/ 1M tokens | $0.13/ 1M tokens | SAVE 37%Official $2.00 |
gpt-5.4Codex Pro External · OpenAI-compatible | $1.25/ 1M tokens | $7.50/ 1M tokens | $0.13/ 1M tokens | SAVE 50%Official $2.50 |
gpt-5.4-miniCodex Pro External · OpenAI-compatible | $0.38/ 1M tokens | $2.25/ 1M tokens | $0.04/ 1M tokens | SAVE 49%Official $0.75 |
gpt-5.5Codex Pro External · OpenAI-compatible | $2.50/ 1M tokens | $15.00/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
gpt-5.6-lunaCodex Pro External · OpenAI-compatible | $0.50/ 1M tokens | $3.00/ 1M tokens | $0.05/ 1M tokens | SAVE 0%Official $0.20 |
gpt-5.6-solCodex Pro External · OpenAI-compatible | $2.50/ 1M tokens | $15.00/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
gpt-5.6-terraCodex Pro External · OpenAI-compatible | $1.25/ 1M tokens | $7.50/ 1M tokens | $0.13/ 1M tokens | SAVE 37%Official $2.00 |
deepseek-v4-flashDeepSeek · OpenAI-compatible | $0.07/ 1M tokens | $0.14/ 1M tokens | $0.00/ 1M tokens | SAVE 50%Official $0.14 |
deepseek-v4-proDeepSeek · OpenAI-compatible | $0.22/ 1M tokens | $0.44/ 1M tokens | $0.00/ 1M tokens | SAVE 49%Official $0.44 |
grok-4.5Grok · xAI / Grok | $1.00/ 1M tokens | $3.00/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $2.00 |
kimi-k2.6Kimi Full K3 · OpenAI-compatible | $0.38/ 1M tokens | $1.75/ 1M tokens | $0.08/ 1M tokens | SAVE 60%Official $0.95 |
kimi-k2.7-codeKimi Full K3 · OpenAI-compatible | $0.38/ 1M tokens | $1.75/ 1M tokens | $0.08/ 1M tokens | SAVE 32%Official $0.56 |
kimi-k3Kimi Full K3 · OpenAI-compatible | $1.50/ 1M tokens | $7.50/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $3.00 |
minimax-m2.5MiniMax · Anthropic | $0.15/ 1M tokens | $0.60/ 1M tokens | $0.02/ 1M tokens | SAVE 50%Official $0.30 |
minimax-m2.7MiniMax · Anthropic | $0.15/ 1M tokens | $0.60/ 1M tokens | $0.03/ 1M tokens | SAVE 50%Official $0.30 |
minimax-m3MiniMax · Anthropic | $0.15/ 1M tokens | $0.60/ 1M tokens | $0.03/ 1M tokens | SAVE 75%Official $0.60 |
deepseek-v4-flashStarter Subscription · OpenAI-compatible | $0.07/ 1M tokens | $0.14/ 1M tokens | $0.00/ 1M tokens | SAVE 50%Official $0.14 |
deepseek-v4-proStarter Subscription · OpenAI-compatible | $0.22/ 1M tokens | $0.44/ 1M tokens | $0.00/ 1M tokens | SAVE 49%Official $0.44 |
glm-5-airZhipu · OpenAI-compatible | $0.06/ 1M tokens | $0.22/ 1M tokens | $0.01/ 1M tokens | SAVE 94%Official $1.00 |
glm-5.5Zhipu · OpenAI-compatible | $0.33/ 1M tokens | $1.35/ 1M tokens | $0.03/ 1M tokens | SAVE 67%Official $1.00 |
glm-5.6Zhipu · OpenAI-compatible | $0.80/ 1M tokens | $3.25/ 1M tokens | $0.08/ 1M tokens | SAVE 20%Official $1.00 |
claude-fable-5claude-code-private · Anthropic | $5.00/ 1M tokens | $25.00/ 1M tokens | $0.50/ 1M tokens | SAVE 50%Official $10.00 |
claude-haiku-4-5claude-code-private · Anthropic | $0.50/ 1M tokens | $2.50/ 1M tokens | $0.05/ 1M tokens | SAVE 50%Official $1.00 |
claude-opus-4-6claude-code-private · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-7claude-code-private · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-opus-4-8claude-code-private · Anthropic | $2.50/ 1M tokens | $12.50/ 1M tokens | $0.25/ 1M tokens | SAVE 50%Official $5.00 |
claude-sonnet-4-6claude-code-private · Anthropic | $1.50/ 1M tokens | $7.50/ 1M tokens | $0.15/ 1M tokens | SAVE 50%Official $3.00 |
claude-sonnet-5claude-code-private · Anthropic | $1.00/ 1M tokens | $5.00/ 1M tokens | $0.10/ 1M tokens | SAVE 50%Official $2.00 |
Pricing note: Rates are displayed in USD per one million tokens and are sourced from Keyvera's public Model Plaza. Prices and model availability can change; the Model Plaza is the operational source of truth before purchase.
Use the same API key, request format, and prepaid balance across supported model routes. Switch the model identifier instead of rebuilding your integration.
The pricing page explains how Keyvera presents AI model API costs in a comparable format. Every displayed rate is normalized to USD per one million tokens so teams can compare workloads before choosing a model route.
Input tokens represent the prompt, system instructions, retrieved context, and conversation history sent to the model. Output tokens represent the response generated by the model. Both dimensions matter because a cheap input route can still become expensive if the workload produces long answers.
Some routes expose cache-read or cache-write prices. These are especially relevant for repeated context, documentation assistants, long-running agents, and retrieval-heavy applications where the same instructions or source material appear across many requests.
Teams should choose models based on the job: reasoning quality, coding performance, latency, context needs, output length, and cost. Keyvera keeps the integration consistent while allowing model choice to stay flexible as workloads change.
Payment processing and order resolution remain inside the authenticated Keyvera application. The landing page publishes public model and pricing information for discovery, comparison, and SEO, but it does not replace the account dashboard or checkout flow.
Transparent token rates. 54 models. One unified API.
Create your account ↗