Models
Every model in the catalog with context window and per-component pricing; each has its own detail page.
One key calls every model below — model ids use vendor names and go straight into the model field.
Alibaba
| Model | Context | Input | Output |
|---|---|---|---|
| aliyun-us/qwen3.8-max | 992K | $2.67 | $8 |
| qwen-flash | 992K | $0.0667 | $0.53 |
| qwen-rerank | 120K | $0.13 | — |
| qwen3.7-plus | 900K | $0.53 | $2.13 |
| qwen3.7-plus-1m | 900K | $1.6 | $6.4 |
| qwen3.7-text-rerank | 120K | $0.0933 | — |
| qwen3.8-flash | 992K | $0.2 | $0.63 |
| qwen3.8-max | 992K | $2.67 | $8 |
| text-embedding-v4 | — | $0.0933 | — |
Anthropic
| Model | Context | Input | Output |
|---|---|---|---|
| claude-fable-5-1 | 240K | $13.33 | $66.67 |
| claude-opus-5-5 | 240K | $5.33 | $26.67 |
| claude-opus-latest | 240K | $5.33 | $26.67 |
| claude-sonnet-5 | 240K | $2.67 | $13.33 |
| claude-sonnet-5.5 | 240K | $2.67 | $13.33 |
BAAI
| Model | Context | Input | Output |
|---|---|---|---|
| bge-m3-embedding | 8K | Free | — |
| bge-m3-reranker | 8K | Free | — |
DeepSeek
| Model | Context | Input | Output |
|---|---|---|---|
| deepseek-flash | 900K | $0.4 | $1.6 |
| deepseek-v4-flash | 900K | $0.4 | $1.6 |
| deepseek-v4-pro | 900K | $1.76 | $5.28 |
| deepseek-v4.1-flash | 900K | $0.4 | $1.6 |
Dots
| Model | Context | Input | Output |
|---|---|---|---|
| dots.mocr | 131K | $0.27 | $0.53 |
| dots.ocr-1.5 | 131K | $0.27 | $0.53 |
| Model | Context | Input | Output |
|---|---|---|---|
| gemini-3-pro-image-preview | 900K | $2.67 | $160 |
| gemini-3.1-flash-image-preview | 900K | $0.67 | $80 |
| gemini-3.1-flash-lite | 900K | $0.33 | $2 |
| gemini-3.1-pro-preview | 900K | $2.67 | $16 |
| gemini-3.5-flash-lite | 900K | $0.4 | $3.33 |
| gemini-3.8-flash | 900K | $1 | $5 |
Moonshot
| Model | Context | Input | Output |
|---|---|---|---|
| kimi-k2.6-turbo | 240K | $2.67 | $10.67 |
| kimi-k3 | 950K | $4 | $20 |
OpenAI
| Model | Context | Input | Output |
|---|---|---|---|
| gpt-5.4 | 240K | $3.33 | $20 |
| gpt-5.4-mini | 240K | $1 | $6 |
| gpt-5.4-nano | 240K | $0.27 | $1.67 |
| gpt-5.5 | 240K | $6.67 | $40 |
| gpt-5.6-terra | 240K | $2.67 | $16 |
| gpt-6-luna | 922K | $0.13 | $0.67 |
| gpt-6.1-sol | 922K | $2.67 | $13.33 |
| gpt-6.1-sol-1m | 922K | $2.67 | $13.33 |
| gpt-image-2 | 240K | $6.67 | $40 |
| gpt-image-2.5-flare | 240K | $6.67 | $40 |
| gpt-image-2.5-sunburst | 240K | $6.67 | $40 |
| text-embedding-3-small | 8K | $0.0267 | — |
xAI
| Model | Context | Input | Output |
|---|---|---|---|
| grok-4.7 | — | $2.67 | $8 |
| grok-latest | — | $2.67 | $8 |
Z.ai
| Model | Context | Input | Output |
|---|---|---|---|
| glm-5.3 | 900K | $1.87 | $5.87 |
| glm-5.3-flash | 900K | $0.2 | $0.67 |
Prices are USD per 1M tokens, refreshed at build time; see the pricing page for the full list.
Choosing a model
| Situation | Suggestion |
|---|---|
| Complex planning, long-context reasoning | A flagship model with a large context window |
| Bulk execution, reformatting, extraction | A fast model — often an order of magnitude cheaper |
| Code generation and refactoring | A mid-tier model that is stable in that language; compare on a small sample first |
| Image understanding | Must support vision, see Vision |
| Embedding / reranking | Embedding or rerank models; no output tokens |
Pricing notes
- Prices are USD per 1M tokens, with input, output and cache-read priced separately
- Prices are regenerated from the pricing catalog at every build, from the same numbers pushed to billing
- Discounts, top-up options and the full price list live on www.tokrouter.dev/pricing
Models change
Vendors add, rename and retire models. For a "definitely available right now" list, call
/v1/models instead of treating this page as availability truth.