claude-fable-5-1
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $10 | $50 | $0.25 |
| Official line−10% vs list | $9 | $45 | $0.225 |
| Shared pool−50% vs list | $5 | $25 | $0.125 |
TopxAI
Loading service details
Loading service details
Where every innovation and reinvention begins.
Claude, GPT, Grok, Kimi and Jev on their official upstreams; GLM and DeepSeek Abliterated are privately deployed fine-tunes. Copy the address below for your SDK. Text is priced in USD per million tokens; other models show their per-image, per-request or per-second unit on each row. Prompts are relayed, never stored.
/v1/messages/v1/chat/completions/v1/responses/v1/images/generations/v1/images/edits/v1/videos/generations/v1/systemoneTwo prices per model: the official line is 90% of the vendor's list price, the shared pool 50%. Compare both routes with the list price, in USD per million tokens. Single-route models are priced at their own ratio to the vendor's list price: GLM-5.3-Abliterated (Private deployment) 286%, kimi-k3.1-pro (Official line) 120%, jev-1.14.0 (Official line) 107%, deepseek-flash-Abliterated (Private deployment) 800%. For models marked with a long-context tier, once the input context reaches the threshold the whole request bills at the higher rate, every token and not just the excess; the threshold and prices are on the line under that model.
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $10 | $50 | $0.25 |
| Official line−10% vs list | $9 | $45 | $0.225 |
| Shared pool−50% vs list | $5 | $25 | $0.125 |
Terms are the ones published on ai.topxea.com.
Claude, GPT, Grok, Kimi and Jev are. ai.topxea.com states that they are served from the official upstream API, with no distilled copies and no third-party mirrors: the official line calls the vendor directly, and the shared pool uses the same upstream at a discounted price. GLM-5.3-Abliterated and DeepSeek Abliterated are privately deployed fine-tunes, not the corresponding vendors' official APIs. The price table labels it "private deployment" and carries its compliance notice on that row.
Same upstream, different routing and price. The official line goes straight to the vendor; the shared pool is discounted: text models cost 50% of the vendor's list price on the shared pool and 90% on the official line. You pick the route when you create a key, or pick "Auto route": one key covers every model, and each request lands on the lowest-priced line that serves its model (shared pool when there is one, otherwise the official line or the model's single route).
Text prices are in USD per million tokens, with input and output counted separately. Other models use the per-image, per-request or per-second unit shown on their row. Long-context, peak/off-peak or resolution tiers follow the conditions shown for that model. You prepay a USD balance by card or USDT / USDC. The usage log records model, tokens, cost and latency for every request.
Claude models work with Claude Code and any Anthropic-compatible SDK or client; GPT and Grok models work with Codex CLI and any OpenAI-compatible SDK or client; GLM and Kimi are served on OpenAI-style /v1/chat/completions only; Jev uses TypeSafe's /v1/systemone, reachable from the official TypeSafe SDKs or agent skill by changing one base URL. The gateway exposes OpenAI-style /v1/chat/completions and /v1/responses alongside Anthropic-style /v1/messages.
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $4 | $20 | $0.2 |
| Official line−10% vs list | $3.6 | $18 | $0.18 |
| Shared pool−50% vs list | $2 | $10 | $0.1 |
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $2 | $10 | $0.1 |
| Official line−10% vs list | $1.8 | $9 | $0.09 |
| Shared pool−50% vs list | $1 | $5 | $0.05 |
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $10 | $50 | $1 |
| Official line−10% vs list | $9 | $45 | $0.9 |
| Shared pool−50% vs list | $5 | $25 | $0.5 |
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $18 / $67.5 · Shared pool $10 / $37.5 · List price $20 / $75 (input / output) | |||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $2 | $10 | $0.1 |
| Official line−10% vs list | $1.8 | $9 | $0.09 |
| Shared pool−50% vs list | $1 | $5 | $0.05 |
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $3.6 / $13.5 · Shared pool $2 / $7.5 · List price $4 / $15 (input / output) | |||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $1 | $5 | $0.05 |
| Official line−10% vs list | $0.9 | $4.5 | $0.045 |
| Shared pool−50% vs list | $0.5 | $2.5 | $0.025 |
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $1.8 / $6.75 · Shared pool $1 / $3.75 · List price $2 / $7.5 (input / output) | |||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $2 | $6 | $0.5 |
| Official line−10% vs list | $1.8 | $5.4 | $0.45 |
| Shared pool−50% vs list | $1 | $3 | $0.25 |
| Long-context tier: From 200,000 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $3.6 / $10.8 · Shared pool $2 / $6 · List price $4 / $12 (input / output) | |||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $1.4 | $4.4 | $0.26 |
| Private deployment+186% / +59% vs list | $4 | $7 | $0.4 |
| Shared pool | This model has one route only, the Private deployment, and no shared pool | ||
| Compliance notice: Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences. | |||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $2 | $10 | $0.2 |
| Official line+20% vs list | $2.4 | $12 | $0.24 |
| Shared pool | This model has one route only, the Official line, and no shared pool | ||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $0.042 | $0 | — |
| Official line+7% vs list | $0.04494 | $0 | — |
| Shared pool | This model has one route only, the Official line, and no shared pool | ||
| Model | Input | Output | Cache read |
|---|---|---|---|
| List price | $0.15 | $0.6 | $0.003 |
| Private deployment+700% / +300% vs list | $1.2 | $2.4 | $0.15 |
| Shared pool | This model has one route only, the Private deployment, and no shared pool | ||
| Compliance notice: Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences. | |||
| Model | List price | Official line10% off | Shared pool50% off | More fields | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Input | Output | Input | Output | Cache read | vs list | Input | Output | Cache read | vs list | ||
| AnthropicVendor's published price | |||||||||||
claude-fable-5-1anthropic · openai | $10 | $50 | $9 | $45 | $0.225 | −10% | $5 | $25 | $0.125 | −50% | |
claude-opus-5-5anthropic · openai | $4 | $20 | $3.6 | $18 | $0.18 | −10% | $2 | $10 | $0.1 | −50% | |
claude-sonnet-5-5anthropic · openai | $2 | $10 | $1.8 | $9 | $0.09 | −10% | $1 | $5 | $0.05 | −50% | |
| OpenAIVendor's published price | |||||||||||
gpt-6-astraopenai · openai-response | $10 | $50 | $9 | $45 | $0.9 | −10% | $5 | $25 | $0.5 | −50% | |
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $18 / $67.5 · Shared pool $10 / $37.5 · List price $20 / $75 (input / output) | |||||||||||
| xAIVendor's published price | |||||||||||
grok-4.7openai · openai-response | $2 | $6 | $1.8 | $5.4 | $0.45 | −10% | $1 | $3 | $0.25 | −50% | |
| Long-context tier: From 200,000 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $3.6 / $10.8 · Shared pool $2 / $6 · List price $4 / $12 (input / output) | |||||||||||
| Zhipu AIVendor's published price | |||||||||||
GLM-5.3-Abliteratedopenai | $1.4 | $4.4 | Private deployment$4 | $7 | $0.4 | +186% / +59% | This model has one route only, the Private deployment, and no shared pool | ||||
| Compliance notice: Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences. | |||||||||||
| Moonshot AIVendor's published price | |||||||||||
kimi-k3.1-proopenai · openai-response | $2 | $10 | $2.4 | $12 | $0.24 | +20% | This model has one route only, the Official line, and no shared pool | ||||
| TypeSafeVendor's published price | |||||||||||
jev-1.14.0systemone | $0.042 | $0 | $0.04494 | $0 | not listed | +7% | This model has one route only, the Official line, and no shared pool | ||||
| DeepSeekVendor's published price | |||||||||||
deepseek-flash-Abliteratedopenai · openai-response | $0.15 | $0.6 | Private deployment$1.2 | $2.4 | $0.15 | +700% / +300% | This model has one route only, the Private deployment, and no shared pool | ||||
| Compliance notice: Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences. | |||||||||||
One route only, no official / shared split. Images are priced by output size: 1K means up to 1024 px on the long side, 2K up to 2048 px. Video is priced per generated second, with a different rate per resolution.
| Model | Price | Reference price |
|---|---|---|
gpt-image-2.5-sunburst/v1/images/generations · /v1/chat/completions · /v1/images/edits | 1K$0.032K$0.05/ image | List price not published |
gpt-image-2.5-flare/v1/images/generations · /v1/chat/completions · /v1/images/edits | 1K$0.032K$0.05/ image | List price not published |
grok-imagine-video-1.5/v1/videos/generations | 480p$0.05720p$0.101080p$0.20/ second | List price not published |
grok-imagine-video-1.5 · Reference price source Vendor's published price ↗ · Verified 2026-10-24 for this model
Support: support@topxea.com, or the help button at the bottom right
User agreement ↗Privacy policy ↗About TopxAI ↗Documentation ↗Price of each model ↗
Source: ai.topxea.com
Vendor list prices verified between 2026-10-24 and 2026-10-30; see each row's details
ai.topxea.com is authoritative
Not on TopxAI's side. ai.topxea.com states zero retention: prompts and completions are relayed, not stored, and the usage log keeps metadata only (model, token counts, cost and latency). Once a request is forwarded, the vendor serving it handles the content under its own API terms and retention settings; the privacy policy says so explicitly.
Limits are set per key: each key can be restricted to specific models, source IPs and a request rate. Your quota is the prepaid balance; a webhook fires when it runs low so you can top up in time.
No, except for verified duplicate charges. This is in the user agreement on ai.topxea.com; read it before you top up.
TopxAI is a new site under TopXEA, the same company behind this store's EA and research lines. The store and AI site share one TopxAI account, so you do not need to register twice. AI balances, API keys and AI service terms remain on ai.topxea.com; store orders and memberships are managed on the main site.
gpt-6.1-solopenai · openai-response | $2 | $10 | $1.8 | $9 | $0.09 | −10% | $1 | $5 | $0.05 | −50% | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $3.6 / $13.5 · Shared pool $2 / $7.5 · List price $4 / $15 (input / output) | |||||||||||
gpt-6.1-terraopenai · openai-response | $1 | $5 | $0.9 | $4.5 | $0.045 | −10% | $0.5 | $2.5 | $0.025 | −50% | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Long-context tier: From 272,001 input tokens the whole request bills at the long-context rate, every token and not just the excess: Official line $1.8 / $6.75 · Shared pool $1 / $3.75 · List price $2 / $7.5 (input / output) | |||||||||||
/v1/chat/completions