AI API pricing comparison
One key for every model. The tables list Wokey and official prices by vendor in USD per 1M tokens. Prices are fixed; a few models have peak and off-peak rates on a fixed daily schedule.
Supply source: From model providers’ official APIs and paid subscriptions; use the open-source project to verify official direct routing—see how it works.
Text model pricing
Unit: USD per 1M tokens. Savings shows the larger of the input and output savings.
Claude (Anthropic)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Claude Haiku 5.5 API claude-haiku-5-5 | $0.08 | $0.4 | $0.008 | $0.1 | $0.5 | 20% |
| Claude Haiku 5.5 API · prompts over 100K | $0.1 | $0.5 | $0.01 | $0.5 | $2.5 | 80% |
Claude Sonnet 5.5 API claude-sonnet-5-5 | $0.3 | $1.5 | $0.015 | $2 | $10 | 85% |
Claude Opus 5.5 API claude-opus-5-5 | $0.6 | $3 | $0.03 | $4 | $20 | 85% |
Claude Fable 5.1 API claude-fable-5-1 | $2.39 | $11.95 | $0.05975 | $10 | $50 | 76% |
Claude Sonnet 5 API claude-sonnet-5 | $0.3 | $1.5 | $0.03 | $2 | $10 | 85% |
Claude Opus 5 API claude-opus-5 | $0.75 | $3.75 | $0.075 | $5 | $25 | 85% |
Claude Fable 5 API claude-fable-5 | $2.39 | $11.95 | $0.239 | $10 | $50 | 76% |
Claude Opus 4.8 API claude-opus-4-8 | $0.75 | $3.75 | $0.075 | $5 | $25 | 85% |
Claude Opus 4.7 API claude-opus-4-7 | $0.75 | $3.75 | $0.075 | $5 | $25 | 85% |
Claude Opus 4.6 API claude-opus-4-6 | $0.75 | $3.75 | $0.075 | $5 | $25 | 85% |
Claude Sonnet 4.6 API claude-sonnet-4-6 | $0.45 | $2.25 | $0.045 | $3 | $15 | 85% |
Claude Haiku 4.5 API claude-haiku-4-5 | $0.2 | $1 | $0.02 | $1 | $5 | 80% |
GPT (OpenAI)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
GPT-6.1 Sol API gpt-6.1-sol | $0.18 | $0.9 | $0.009 | $2 | $10 | 91% |
GPT-6 Sol API gpt-6-sol | $0.18 | $0.9 | $0.018 | $2 | $10 | 91% |
GPT-6 Luna API gpt-6-luna | $0.09 | $0.45 | $0.009 | $0.1 | $0.5 | 10% |
GPT-6 Astra API gpt-6-astra | $0.55 | $2.75 | $0.055 | $10 | $50 | 95% |
GPT-5.6 Sol API gpt-5.6-sol | $0.44 | $2.2 | $0.044 | $4 | $20 | 89% |
GPT-5.6 Terra API gpt-5.6-terra | $0.2 | $1.2 | $0.02 | $2 | $12 | 90% |
GPT-5.6 Luna API gpt-5.6-luna | $0.12 | $0.72 | $0.012 | $0.2 | $1.2 | 40% |
GPT-5.5 API gpt-5.5 | $0.5 | $3 | $0.05 | $5 | $30 | 90% |
Kimi (Moonshot AI)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Kimi K2.8 Preview API kimi-for-coding | $0.3 | $1.2 | $0.075 | $1 | $4 | 70% |
Kimi K3 API kimi-k3 | $0.9 | $4.5 | $0.09 | $3 | $15 | 70% |
GLM (Zhipu)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
GLM-5.3-Flash API glm-5.3-flash | $0.075 | $0.25 | $0.015 | $0.15 | $0.5 | 50% |
GLM-5.3 API glm-5.3 | $0.28 | $0.88 | $0.052 | $1.4 | $4.4 | 80% |
Grok (xAI)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Grok 4.7 API grok-4.7 | $0.28 | $0.84 | $0.07 | $2 | $6 | 86% |
Grok 4.6 API grok-4.6 | $0.28 | $0.84 | $0.07 | $2 | $6 | 86% |
Grok 4.5 API grok-4.5 | $0.28 | $0.84 | $0.028 | $2 | $6 | 86% |
Grok 4.3 API grok-4.3 | $0.1875 | $0.375 | $0.01875 | $1.25 | $2.5 | 85% |
DeepSeek
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
DeepSeek-V4.1-Flash API deepseek-flash | $0.105 | $0.42 | $0.0021 | $0.15 | $0.6 | 30% |
MiniMax
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
MiniMax M3.1 Flash API MiniMax-M3.1-Flash | $0.075 | $0.3 | $0.0075 | $0.15 | $0.6 | 50% |
MiniMax M3 API MiniMax-M3 | $0.09 | $0.36 | $0.018 | $0.45 | $1.8 | 80% |
Gemini (Google)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Gemini 3.5 Flash API gemini-3.5-flash (paused) | $0.3 | $1.8 | $0.03 | $1.5 | $9 | 80% |
Qwen
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Qwen 3.8 Max API qwen3.8-max (paused) | $0.345 | $1.035 | $0.069 | $1.725 | $5.175 | 80% |
Qwen 3.7 Plus API qwen3.7-plus (paused) | $0.0575 | $0.23 | $0.0115 | $0.2875 | $1.15 | 80% |
Doubao (Volcengine Ark)
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
DeepSeek V4 Flash API deepseek-v4-flash | $0.112 | $0.448 | $0.00224 | $0.15 | $0.6 | 25% |
Doubao Seed 2.1 Pro API doubao-seed-2.1-pro | $0.1725 | $0.8625 | $0.0345 | $0.8625 | $4.3125 | 80% |
Doubao Seed 2.1 Lite API doubao-seed-2.1-lite | $0.0575 | $0.194062 | $0.0115 | $0.115 | $0.388125 | 50% |
Doubao Seed 2.0 Mini API doubao-seed-2.0-mini | $0.0575 | $0.575 | $0.0115 | $0.115 | $1.15 | 50% |
DeepSeek V4 Pro API deepseek-v4-pro | $0.528 | $1.584 | $0.0176 | $0.66 | $1.98 | 20% |
OpenCode Go
| Model | Input | Output | Cache read | Official input | Official output | Savings |
|---|---|---|---|---|---|---|
Gemini 4 Argon Contributor API gemini-4-argon-contributorOpenCode Go quota rate · Vs Go rate | $1.2 | $6 | $0.06 | $4 | $20 | 70% |
LongCat-2.0 API longcat-2.0 | $0.15 | $0.6 | $0.003 | $0.3 | $1.2 | 50% |
Muse Spark 1.3 Contributor API muse-spark-1.3-contributor | $0.1 | $0.2 | $0.002 | $0.1 | $0.2 | — |
Tencent Hy4 Preview API hy4-preview | $0.417 | $1.2505 | $0.021 | $0.834 | $2.501 | 50% |
FAQ
Do prices change?
The listed prices are fixed. A few models have peak and off-peak rates on a fixed daily schedule, marked in the table. Any price change is announced on this page in advance.
How do I use it with Claude Code or Codex?
Point the client’s base URL at Wokey and use your Wokey API key; no code changes. The guides list the exact settings.