Everything on this page comes live from the API (GET /v1/models and GET /v1/pools) โ the same data you get when you call it yourself. It re-syncs every hour.
# Models you can name directly (main + selectable side)
curl https://tokentable.asia/v1/models
# Side-model pools Auto uses
curl https://tokentable.asia/v1/pools
# See which model served this request
curl -si https://tokentable.asia/v1/chat/completions \
-H "Authorization: Bearer tt-live-..." \
-H "Content-Type: application/json" \
-d '{"model":"auto","messages":[{"role":"user","content":"hi"}]}' \
| grep -i '^x-tt-'Put a model ID from the table into the model field to use it. The multiplier is how many main-quota points one call uses; leave it out or send "auto" to let the router choose.
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| claude-fable-5 | Most capable (selectable)Paid plans | 1M | 10ร |
| claude-fable-5-1 | Most capable (latest, selectable)Paid plans | 1M | 10ร |
| claude-opus-4-8 | Flagship reasoning | 1M | 6ร |
| claude-opus-5 | Latest flagship reasoning (selectable) | 1M | 6ร |
| claude-sonnet-4-6 | Fast + intelligent | 1M | 4ร |
| claude-sonnet-5 | Sonnet flagship (selectable) | 1M | 4ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| gpt-5.5 | General purpose | 1M | 8ร |
| gpt-5.6 | GPT flagship โ Sol (selectable) | 1M | 5ร |
| gpt-5.6-luna | GPT flagship โ Luna (cost-efficient, selectable) | 1M | 1ร |
| gpt-5.6-terra | GPT flagship โ Terra (balanced, selectable) | 1M | 4ร |
| gpt-6-astra | GPT-6 flagship (selectable)Paid plans | 1M | 10ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| grok-4.20-0309-non-reasoning | Grok next-gen (selectable) | 1M | 2ร |
| grok-4.20-0309-reasoning | Grok next-gen reasoning (selectable) | 1M | 3ร |
| grok-4.3 | Real-time web | 256k | 2ร |
| grok-4.5 | Grok reasoning (selectable) | 256k | 4ร |
| grok-4.6 | Grok flagship (new) | 500k | 4ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| gemini-3.5-flash | Gemini flagship | 1M | 3ร |
| gemini-3.6-flash | Gemini next-gen (selectable) | 1M | 3ร |
| gemini-3.8-flash | Gemini latest (selectable) | 1M | 3ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| mistral-large-latest | Mistral Large (EU) | 256k | 2ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| deepseek-ai/DeepSeek-V4.1-Flash | DeepSeek V4.1 Flash (selectable) | 1M | 2ร |
| zai-org/GLM-5.3-Flash | Zhipu GLM Flash (selectable) | 1M | 1ร |
| Model ID | Description | Context | Multiplier |
|---|---|---|---|
| qwen-flash | Qwen fast (low-latency) | 1M | 1ร |
| qwen-plus | Qwen classic flagship | 1M | 1ร |
| qwen3-max | CN max (selectable) | 256k | 2ร |
| qwen3.5-plus | Qwen3.5 Plus vision-language (selectable) | 1M | 2ร |
| qwen3.6-plus | CN flagship | 1M | 1ร |
| qwen3.7-max | CN agent flagship (new) | 1M | 3ร |
| qwen3.7-plus | CN vision flagship (new) | 1M | 2ร |
| qwen3.8-max | CN flagship (new, vision) | 1M | 3ร |
| deepseek-v4-flash | Deep reasoning Flash (new) | 1M | 1ร |
| deepseek-v4-pro | Deep reasoning Pro | 128k | 1ร |
| kimi-k2-thinking | Kimi K2 thinking (selectable) | 256k | 2ร |
| kimi-k2.5 | Kimi K2.5 coding (selectable) | 256k | 2ร |
| kimi-k2.6 | Coding flagship | 128k | 1ร |
| kimi-k2.7-code | Kimi K2.7 coding (new) | 256k | 2ร |
| kimi/kimi-k3 | Kimi K3 flagship (selectable) | 1M | 5ร |
| glm-5.1 | Zhipu GLM (selectable) | 1M | 2ร |
| glm-5.2 | Zhipu GLM flagship (new) | 1M | 2ร |
| ZHIPU/GLM-5.3 | Zhipu GLM next-gen (selectable) | 1M | 2ร |
| MiniMax-M2.5 | CN text (selectable) | 1M | 1ร |
| MiniMax/MiniMax-M2.7 | CN agentic (MiniMax M2.7) | 1M | 2ร |
| MiniMax/MiniMax-M3 | CN flagship (MiniMax M3, MSA) | 1M | 2ร |
| unisound/unisound-u2 | Unisound U2 agent flagship (selectable) | 160k | 2ร |
| xiaomi/mimo-v2.5-pro | Xiaomi MiMo flagship (new) | 1M | 1ร |
Side models are grouped by what you want to do. With Auto (or no model set), the router picks from the matching pool. Current representative models for each pool are listed below.
Everyday chat, writing, summaries
Code generation, bug fixes, code review
Complex logic, multi-step reasoning, deep analysis
Very long documents, whole books, large data
Translation between languages
Document processing, reports, office work
Image understanding, screenshot Q&A, OCR (selectable)
Text-to-image illustrations and product shots (selectable)
Text or image to short video (selectable)
Text-to-speech
Pool contents change with provider availability. Image, video and voice generation use a fixed number of points per call; some advanced image/video models need to be enabled first โ sign in to see them in your dashboard.
This list re-syncs with the API every hour. For your own usage and enabled models, go to the dashboard