Run coding agents alongside API, image, and video workloads through one reliable access layer. Centralize routing, keys, quotas, failover, and usage across every team.
https://api.hop-base.com/v1
HopBase provides one stable control layer for routing, failover, access controls, and usage tracking across coding, API, image, and video workloads.
Handle batch workloads, shared development environments, and traffic spikes across business lines. Automatic multi-channel failover maintains availability, with concurrency sized to your workload.
Use stable, continuously maintained channels for Claude, Codex, OpenAI, and AWS Bedrock, built for long-running workloads and advanced reasoning.
Segment API keys, quotas, and billing by organization, project, team, or customer. Use the same controls for internal platforms and multi-tenant products.
Track every call by model usage for departmental chargebacks, customer billing, margin analysis, and usage audits.
Keep your OpenAI or Anthropic SDK and change only the base URL to route through one access layer.
You pay the discounted channel rate × actual usage. Official list prices are shown only as a benchmark. Because rates vary by channel, review one channel at a time.
| Model ID | Official list price | Max limited-time offer | Savings vs. list | Notes |
|---|---|---|---|---|
| claude-fable-5 Flagship | $10 / $50 | $3 / $16Read $0.31 · Write $3.92 / $6.26 | save ~69% | Latest high-reasoning model |
| claude-opus-5 New | $5 / $25 | $1.5 / $8Read $0.16 · Write $1.96 / $3.13 | save ~69% | Next-gen Opus workhorse |
| claude-opus-4-8 Recommended | $5 / $25 | $1.5 / $8Read $0.16 · Write $1.96 / $3.13 | save ~69% | Top reasoning for heavy Claude Code tasks |
| claude-opus-4-7 | $5 / $25 | $1.5 / $8Read $0.16 · Write $1.96 / $3.13 | save ~69% | 1M-context Opus |
| claude-opus-4-6 | $5 / $25 | $1.5 / $8Read $0.16 · Write $1.96 / $3.13 | save ~69% | 1M-context Opus |
| claude-opus-4-5-20251101 | $5 / $25 | $1.5 / $8Read $0.16 · Write $1.96 / $3.13 | save ~69% | Short alias claude-opus-4-5 |
| claude-sonnet-5 New | $3 / $15 | $0.95 / $4.5Read $0.094 · Write $1.18 / $1.88 | save ~69% | Next-gen Sonnet workhorse |
| claude-sonnet-4-6 Balanced | $3 / $15 | $0.95 / $4.5Read $0.094 · Write $1.18 / $1.88 | save ~69% | Balanced workhorse for long context |
| claude-sonnet-4-5-20250929 | $3 / $15 | $0.95 / $4.5Read $0.094 · Write $1.18 / $1.88 | save ~69% | Short alias claude-sonnet-4-5 |
| claude-sonnet-4-20250514 Deprecated / auto-routed to 4.6 | $3 / $15 | $0.95 / $4.5Read $0.094 · Write $1.18 / $1.88 | save ~69% | Legacy ID auto-routes to claude-sonnet-4-6 |
| claude-haiku-4-5-20251001 | $1 / $5 | $0.3 / $1.5Read $0.031 · Write $0.39 / $0.63 | save ~69% | Lightweight, low-cost model |
| Model ID | Official list price | AWS Bedrock | Prompt Cache | Notes |
|---|---|---|---|---|
| claude-opus-4-8 Recommended | $5 / $25 | $2.5 / $1351% · save ~49% | Read $0.26Write 5m $3.22 / 1h $5.15 | Top reasoning, ideal for heavy Claude Code tasks |
| claude-opus-4-7 / 4-6 | $5 / $25 | $2.5 / $1351% · save ~49% | Read $0.26Write 5m $3.22 / 1h $5.15 | Opus series — complex planning & long tasks |
| claude-opus-4-5-20251101 | $5 / $25 | $2.5 / $1351% · save ~49% | Read $0.26Write 5m $3.22 / 1h $5.15 | Short alias claude-opus-4-5 |
| Model ID | Official list price | Full-quota Max / Kiro | Savings vs. list | Notes |
|---|---|---|---|---|
| claude-fable-5 Flagship | $10 / $50 | $3.5 / $18Read $0.37 · Write $4.6 / $7.35 | 37% · save ~63% | Latest high-reasoning model |
| claude-opus-5 New | $5 / $25 | $2 / $9Read $0.18 · Write $2.3 / $3.68 | 37% · save ~63% | Next-gen Opus workhorse |
| claude-opus-4-8 Recommended | $5 / $25 | $2 / $9Read $0.18 · Write $2.3 / $3.68 | 37% · save ~63% | Top reasoning for heavy Claude Code tasks |
| claude-opus-4-7 / 4-6 | $5 / $25 | $2 / $9Read $0.18 · Write $2.3 / $3.68 | 37% · save ~63% | 1M-context Opus |
| claude-opus-4-5-20251101 | $5 / $25 | $2 / $9Read $0.18 · Write $2.3 / $3.68 | 37% · save ~63% | Short alias claude-opus-4-5 |
| claude-sonnet-5 New | $3 / $15 | $1 / $5.5Read $0.11 · Write $1.38 / $2.21 | 37% · save ~63% | Next-gen Sonnet workhorse |
| claude-sonnet-4-6 Balanced | $3 / $15 | $1 / $5.5Read $0.11 · Write $1.38 / $2.21 | 37% · save ~63% | Balanced workhorse for long context |
| claude-sonnet-4-5-20250929 | $3 / $15 | $1 / $5.5Read $0.11 · Write $1.38 / $2.21 | 37% · save ~63% | Short alias claude-sonnet-4-5 |
| claude-sonnet-4-20250514 Deprecated / auto-routed to 4.6 | $3 / $15 | $1 / $5.5Read $0.11 · Write $1.38 / $2.21 | 37% · save ~63% | Legacy ID auto-routes to claude-sonnet-4-6 |
| claude-haiku-4-5-20251001 | $1 / $5 | $0.35 / $2Read $0.037 · Write $0.46 / $0.74 | 37% · save ~63% | Lightweight, low-cost model |
› Prices are in USD per 1 million tokens (input / output). Model availability is shown in the console.
| Model ID | Official list price | Codex Plus | Codex Pro | Notes |
|---|---|---|---|---|
| gpt-5.6 / -sol New | $5 / $30Cached $0.5 | $0.35 / $26.6% · Cached $0.033 | $0.45 / $2.58.8% · Cached $0.044 | Next-gen flagship · 1.05M context, tiered above 272K |
| gpt-5.6-terra New | $2.5 / $15Cached $0.25 | $0.15 / $16.6% · Cached $0.017 | $0.2 / $1.58.8% · Cached $0.022 | 5.6 balanced tier · 1.05M context |
| gpt-5.6-luna New | $1 / $6Cached $0.1 | $0.07 / $0.46.6% · Cached $0.007 | $0.09 / $0.58.8% · Cached $0.009 | 5.6 light tier · low latency & cost |
| gpt-5.5 Core | $5 / $30Cached $0.5 | $0.35 / $26.6% · Cached $0.033 | $0.45 / $2.58.8% · Cached $0.044 | Complex reasoning & Codex flagship |
| gpt-5.4 | $2.5 / $15Cached $0.25 | $0.15 / $16.6% · Cached $0.017 | $0.2 / $1.58.8% · Cached $0.022 | Tiered multiplier above 272K context |
| gpt-5.4-mini | $0.75 / $4.5Cached $0.075 | $0.05 / $0.36.6% · Cached $0.005 | $0.07 / $0.48.8% · Cached $0.007 | Low latency, low cost |
| gpt-5.3-codex-spark | $1.75 / $14Cached $0.175 | $0.1 / $0.956.6% · Cached $0.012 | $0.15 / $18.8% · Cached $0.015 | Codex lightweight tasks |
| gpt-image-1 / 1.5 / 2 Image | $5 / $30Cached $0.5 | $0.35 / $26.6% · Cached $0.033 | $0.45 / $2.58.8% · Cached $0.044 | Image APIs billed by actual token usage |
› Prices are in USD per 1 million tokens (input / output). Image models are billed by token usage; a standard 1K image typically costs about $0.09.
| Model ID | Official list price | Gemini channel | API interface | Notes |
|---|---|---|---|---|
| gemini-3.6-flash New | $1.5 / $7.5Cached $0.15 | $0.68 / $3.4246% · Cached $0.068 | v1beta only | Next-gen Flash workhorse |
| gemini-3.5-flash | $1.5 / $9Cached $0.15 | $0.68 / $4.1046% · Cached $0.068 | OpenAI-compatible · v1beta | Balanced Flash tier |
| gemini-3.5-flash-lite | $0.3 / $2.5Cached $0.03 | $0.14 / $1.1446% · Cached $0.014 | v1beta only | Low latency, low cost |
| gemini-3.1-pro-preview / -customtools | $2 / $12Cached $0.2 | $0.91 / $5.4746% · Cached $0.091 | OpenAI-compatible · v1beta | Pro reasoning & long context |
| gemini-3-flash-preview | $0.5 / $3Cached $0.05 | $0.23 / $1.3746% · Cached $0.023 | OpenAI-compatible · v1beta | Low latency, low cost |
| gemini-3.1-flash-lite / -preview | $0.25 / $1.5Cached $0.025 | $0.11 / $0.6846% · Cached $0.011 | OpenAI-compatible · v1beta | Low latency, low cost |
| gemini-2.5-pro | $1.25 / $10Cached $0.125 | $0.57 / $4.5646% · Cached $0.057 | v1beta only | 2.5-series Pro |
| gemini-2.5-flash | $0.3 / $2.5Cached $0.03 | $0.14 / $1.1446% · Cached $0.014 | v1beta only | 2.5-series Flash |
| gemini-2.5-flash-lite | $0.1 / $0.4Cached $0.01 | $0.05 / $0.1846% · Cached $0.005 | v1beta only | Low latency, low cost |
| gemini-omni-flash-preview Video | $1.5 / $9Cached $0.15 | $0.68 / $4.1046% · Cached $0.068 | v1beta only | Omni multimodal · video generation |
| gemini-3-pro-image / -preview Image | $2 / $12Cached $0.2 | $0.91 / $5.4746% · Cached $0.091 | OpenAI-compatible · v1beta | Pro image generation |
| gemini-3.1-flash-image / -preview Image | $0.5 / $3Cached $0.05 | $0.23 / $1.3746% · Cached $0.023 | OpenAI-compatible · v1beta | Flash image generation |
| gemini-3.1-flash-lite-image Image | $0.25 / $1.5Cached $0.025 | $0.11 / $0.6846% · Cached $0.011 | OpenAI-compatible · v1beta | Flash image generation |
| gemini-2.5-flash-image Image | $0.3 / $30Cached $0.03 | $0.14 / $13.6846% · Cached $0.014 | OpenAI-compatible · v1beta | Nano Banana image editing |
› Prices are in USD per 1 million tokens (input / output). Cache shows the prompt-cache read rate. Pricing is about 46% of the official base rate (¥3.10 per US$1 of list price). Available interfaces: OpenAI-compatible via Azure (/v1/chat/completions) and native Gemini v1beta via direct provider access. Check the API interface column and console for per-model availability.
| Model ID | Official list price | GLM channel | Rate vs. list | Notes |
|---|---|---|---|---|
| glm-5.2 1M context | $1.40 / $4.40z.ai official list · Cached $0.26 | $0.77 / $2.4255% · Cached $0.14 | save ~45% | OpenAI-compatible /v1/chat/completions |
› Rate vs. list = your price ÷ the official USD list price, converted at ¥6.8/USD and calculated from input rates. Final charges are shown in the console.
Seedance · Video
| Tier | Model ID | Resolution | Text-to-video | Image-to-video (with reference) |
|---|---|---|---|---|
| Standard | dreamina-seedance-2-0-hc dreamina-seedance-2-0-ep dreamina-seedance-2-0-260128 | 480p / 720p | $6.30 | $3.87 |
| 1080p | $6.93 | $4.23 | ||
| 4k | $3.60 | $2.16 | ||
| Fast | dreamina-seedance-2-0-fast-hc dreamina-seedance-2-0-fast-ep dreamina-seedance-2-0-fast-260128 | 480p / 720p | $5.04 | $2.97 |
| Mini | dreamina-seedance-2-0-mini-hc dreamina-seedance-2-0-mini-ep dreamina-seedance-2-0-mini-260615 | 480p / 720p | $3.15 | $1.89 |
Seedream · Image
| Model ID | Resolution | Official list price | Seedream channel | Notes |
|---|---|---|---|---|
| seedream-5-0-pro Recommended | 1K / 2K · PNG / JPEG · standard / fast | $0.045 / $0.09≤2.36MP / >2.36MP | $0.0306 / $0.061268% | Text-to-image / image-to-image / partial edits |
| seedream-5-0-lite | 2K / 3K / 4K · PNG / JPEG · standard | $0.035 | $0.023868% | Seedream 5.0 Lite |
| seedream-4-5 | 2K / 4K · JPEG · standard | $0.04 | $0.027268% | Previous-gen image workhorse |
› Video prices are in USD per 1 million video tokens; usage increases with resolution, frame rate, and duration. Mini at 480p for 5 seconds costs about $0.15, and video links remain active for 24 hours. Image prices are per generated image at 68% of the official base rate. See the docs for details.
Give this prompt to Claude Code, Codex, Cursor, or another coding agent. It will read the HopBase llms.txt index, find the relevant docs, and answer with the right model and endpoint.
Straight answers on scale, reliability, pricing, and integration. See the docs for implementation details, or contact us about your workload.
Yes. HopBase provides one gateway for enterprises, one-person companies (OPCs), and teams across multiple business lines. Gateway-level groups, quotas, and cost tracking support batch jobs, shared team access, and production workloads. Concurrency is sized to your use case.
Most API proxies simply route requests through a single account, which limits reliability and operational control. HopBase adds high-concurrency routing, automatic multi-channel failover, scoped keys, quotas, and cost tracking for sustained production use.
HopBase keeps personal accounts out of your integration. You connect with enterprise API keys; AWS Bedrock requires no personal Claude login, and other Claude, Codex, and OpenAI channels are governed by group permissions.
HopBase supports Claude Fable 5, Opus 5, Sonnet 5, and the Opus and Haiku families; OpenAI GPT and Codex models; Gemini; GLM 5.2; Seedream image models; and Seedance video models. AWS Bedrock currently supports Opus models only. See the console for the complete model list.
Claude Max offers the lowest limited-time rate at about 31% of list for frequent, cost-sensitive workloads. AWS Bedrock connects directly to AWS without a personal login, costs about 51% of list, and currently supports Opus models only. Claude Max (full quota) / Kiro provides higher quotas at about 37% of list. Choose based on budget, model coverage, and reliability requirements.
HopBase rates are approximately 31% of list for Claude Max, 51% for AWS Bedrock, 37% for Claude Max (full quota) / Kiro, 6.6% for Codex, and 55% for GLM 5.2. Each percentage is your rate divided by the comparable official list price, using ¥6.8/USD where conversion is required. Billing is based on actual usage.
No. Prepaid credits have no expiration date and remain available while your account is active.
HopBase provides one integration and one governance layer across providers. Keep Claude Code, Codex, and your OpenAI or Anthropic SDK while adding scoped keys, quotas, cost allocation, and usage auditing.
Tell us what you run, how much concurrency you need, and which models matter. We’ll recommend the right channels and help configure your keys and SDKs.
View pricing