// Included. No token meter.Unlimited Kimi K3 and DeepSeek V4.1 Flash for $200 a month
- Kimi K3
- Unlimited
- DeepSeek V4.1 Flash
- Unlimited
- Other models
- Per token
- Available to
- Individuals only
| Model | Uncached input | Output |
|---|---|---|
| Kimi K3 | 24,290 | 6,162 |
| DeepSeek V4.1 Flash | 701,079 | 76,559 |
Unlimited means no token meter and no limit on total tokens. Each subscription has these rate limits for each model, and requests can also be rate limited when we are at capacity.
One price,
no token meter
What the plan covers
Kimi K3 and DeepSeek V4.1 Flash, with no token meter and no monthly token cap. Every other Morph model bills per token at list price, from your credits first, then your card.
morph-kimik3 // Kimi K3morph-kimik31 // Kimi K3.1morph-dsv41flash // DeepSeek V4.1 Flashmorph-dsv41flash-1017 // October 17 snapshot // Without the plan, per 1M tokens// Kimi K3 $2.50 in, $0.29 cached, $14.00 out// V4.1 Flash $0.12 in, $0.008 cached, $0.80 outRate limits
Unlimited removes the token meter. It does not reserve capacity. There is no limit on total tokens, only on how fast you use them. Each subscription has per-minute rate limits on uncached input and output tokens for each model, so no account can crowd out the rest. Cached input does not count toward them. Requests can also return 429 when we are at capacity.
// Per subscription, tokens per minute// Model Uncached input Output// Kimi K3 24,290 6,162// DeepSeek V4.1 Flash 701,079 76,559 // A 429 means retry. The SDK handles it.const client = new OpenAI({ apiKey: process.env.MORPH_API_KEY, baseURL: "https://api.morphllm.com/v1", maxRetries: 5, // backs off and honors Retry-After});Point your agent at it
Morph serves the OpenAI and Anthropic wire formats. Two environment variables move Claude Code onto the plan.
export ANTHROPIC_BASE_URL="https://api.morphllm.com"export ANTHROPIC_AUTH_TOKEN="YOUR_MORPH_API_KEY"export ANTHROPIC_MODEL="morph-kimik3"export ANTHROPIC_SMALL_FAST_MODEL="morph-dsv41flash"claude