Tokens vs Moonshot Kimi API
Moonshot sells Kimi K3 and K2.x at flat prices in OpenAI and Anthropic formats. Tokens adds BDT billing and other providers on the same key.
Moonshot's own platform (platform.kimi.ai, formerly platform.moonshot.ai) is where Kimi's list prices come from: Kimi K3 is $3 / $15 per million tokens with $0.30 cache hits, and K2.6 and K2.7 Code are $0.95 / $4.00, with no context-length tiers. Its API accepts both OpenAI and Anthropic request formats. K3 cache writes are billed separately ($3 per million for a 5-minute TTL, $6 for 1 hour), and Moonshot retires older models on its own schedule: K2.5 was discontinued on 31 August 2026. Tokens suits developers who use Kimi alongside Claude, GPT, DeepSeek or GLM and want one key, one BDT invoice and per-key spend caps. If Kimi is your only model and paying in USD is easy, direct is simpler.
Tokens
- Pricing model
- Prepaid plan or USD wallet, paid in BDT; per-model prices in USD and BDT on /models
- Payment methods
- Invoice via billing portal
- Currencies
- USD and BDT
- Model prices
- Live in the model catalog, in BDT and USD
Moonshot Kimi API
- Pricing model
- Prepaid account balance; flat per-token USD prices with no context tiers; K3 cache writes billed separately
- Payment methods
- Prepaid account balance, recharged in the Kimi console, USD prices; tax calculated at checkout
- Prices checked
- 3 Oct 2026
- Kimi K3 (per 1M tokens, in / out)
- $3.00 / $15.00
- Kimi K3 cache hit (per 1M tokens)
- $0.30
- Kimi K2.6 (per 1M tokens, in / out)
- $0.95 / $4.00
- Kimi K2.7 Code (per 1M tokens, in / out)
- $0.95 / $4.00
- Kimi K2.7 Code HighSpeed (per 1M tokens, in / out)
- $1.90 / $8.00
Side by side
| Topic | Tokens | Moonshot Kimi API |
|---|---|---|
| Price | Set per model by Tokens; see /models | Moonshot's list price, flat across the context window |
| API formats | OpenAI-compatible at https://tokens.bd/v1, Anthropic-compatible at https://tokens.bd | OpenAI and Anthropic formats on Moonshot's API |
| Paying from Bangladesh | BDT invoice through the billing portal | Prepaid recharge with USD prices. Bangladesh Bank FE Circular 26 (2019) limits international-card online payments to USD 300 per transaction |
| Providers on one key | Kimi plus Claude, GPT, Gemini, DeepSeek, GLM, Qwen and others | Kimi models only |
| Model lifecycle | Admin-managed catalog; check /models or GET /v1/models for current Kimi ids | Retires models on its own schedule (K2 series in May 2026, K2.5 on 31 Aug 2026) |
| Spend control | Monthly cap and model allow-list per key; alerts at 50/75/90/100% and on low balance | Spending is bounded by the prepaid balance |
| Network path | One extra gateway hop | Direct to the model maker |
Choose Tokens when
- Pay a BDT invoice instead of recharging a USD balance with an international card.
- Run Kimi K3 in Claude Code or OpenCode and switch to Claude, GPT or GLM without a second account.
- Per-key spend caps matter with K3, whose output costs $15 per million tokens at list price.
- Receipts, usage history and support tickets in one dashboard.
Choose Moonshot Kimi API when
- Moonshot's list price is the floor; check /models for Tokens' Kimi prices.
- New Kimi models and features appear on Moonshot's platform first.
- Adds a gateway hop and one more party in the data path (Tokens does not store prompt or response content).
Switch your client
# Before: OPENAI_BASE_URL=https://api.moonshot.ai/v1, model kimi-k3 export TOKENS_API_KEY=tok_live_your_key export OPENAI_BASE_URL=https://tokens.bd/v1 export OPENAI_API_KEY=$TOKENS_API_KEY # Kimi ids on Tokens use provider/model form; find them with: curl -s https://tokens.bd/v1/models -H "Authorization: Bearer $TOKENS_API_KEY" | grep -i kimi # Anthropic-format clients such as Claude Code export ANTHROPIC_BASE_URL=https://tokens.bd export ANTHROPIC_AUTH_TOKEN=$TOKENS_API_KEY
Other comparisons
- Tokens vsAlibaba Cloud Qwen API (Model Studio)Alibaba Model Studio sets Qwen's list prices, with regional rates and input-length tiers. Tokens bills Qwen in BDT beside other providers.
- Tokens vsAnthropic API (Claude)Anthropic's API has Claude at list price, a half-price Batch API and first-party tools. Tokens puts Claude next to other providers on one BDT-billed key.
- Tokens vsCommand CodeCommand Code is a coding agent sold with credit plans from $1/month. Tokens is a gateway, paid in BDT, for the agents you already use.
- Tokens vsDeepSeek APIDeepSeek's own API sets the list price for its models and halves it off-peak. Tokens adds BDT billing and other providers on the same key.
- Tokens vsGoogle Gemini APIGoogle's Gemini API has a free tier, Batch at half price and Search grounding. Tokens serves Gemini Flash in OpenAI and Anthropic formats, billed in BDT.
- Tokens vsOpenAI APIOpenAI's API has GPT at list price with Batch and Flex at half price. Tokens puts GPT beside Claude, Gemini and open models on one key billed in BDT.
- Tokens vsOpenCode ZenZen sells tested coding models at cost plus card fees, and OpenCode Go adds $10 and $40 plans. Tokens bills in BDT with one base URL per API format.
- Tokens vsOpenRouterOpenRouter has the larger catalog, free models and fine routing controls. Tokens lets you pay in BDT and sets spend caps and model lists per key.
- Tokens vsZ.ai GLM APIZ.ai sells GLM-5.3 and GLM-5.3 Flash at flat list prices, plus a GLM Coding Plan from $18/month. Tokens bills GLM in BDT beside other providers.