Tokens vs OpenCode Zen
Zen 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.
OpenCode Zen is the gateway run by the OpenCode team: a tested list of coding models sold pay-as-you-go at provider cost, with card fees passed through (4.4% + $0.30). OpenCode Go adds $10 and $40 monthly plans with per-model dollar limits, and Zen lists a dozen models that are free for a limited time. The endpoint depends on the model: Responses for GPT, Messages for Claude, Chat Completions for DeepSeek, GLM and Kimi, and a Google-style path for Gemini. Tokens suits developers who want to pay a BDT invoice, keep one OpenAI-compatible and one Anthropic-compatible base URL for every model, and put a spend cap and model allow-list on each key. If you work mostly inside OpenCode and paying by card is no trouble, Zen or Go is the simpler choice, since it is built into the agent.
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
OpenCode Zen
- Pricing model
- Pay-as-you-go at provider cost plus card fee (4.4% + $0.30); OpenCode Go plans at $10 or $40/month with per-model limits
- Payment methods
- Card in USD (Stripe)
- Prices checked
- 3 Oct 2026, Zen pay-as-you-go, before card fee
- GLM-5.3 (per 1M tokens, in / out)
- $1.40 / $4.40
- Kimi K3 (per 1M tokens, in / out)
- $3.00 / $15.00
- MiniMax M3 (per 1M tokens, in / out)
- $0.30 / $1.20
- Qwen 3.8 Max (per 1M tokens, in / out)
- $2.00 / $6.00
- DeepSeek V4.1 Flash (per 1M tokens, in / out)
- $0.30 / $1.20
- GPT-6 Luna, up to 272K (per 1M tokens, in / out)
- $0.10 / $0.50
Side by side
A tick marks the better option for that row. Some rows go to the other side.
| Topic | Tokens | OpenCode Zen |
|---|---|---|
| Paying from Bangladesh | BDT invoice through the billing portal; no international card needed | USD card through Stripe ($20 default top-up plus $1.23 fee). International cards fall under Bangladesh Bank FE Circular 26 (2019): USD 300 per online transaction |
| Endpoints | https://tokens.bd/v1 for OpenAI formats and https://tokens.bd for Anthropic Messages, same key for all models | Fixed per model family: /zen/v1/responses, /messages, /chat/completions, or a Google-style path for Gemini |
| Inside OpenCode | Custom provider entry (tokens/<model>), written for you by the setup CLI | Built-in provider, connected with /connect |
| Subscriptions | Weekly or monthly plans with a credit allowance and usage windows, renewed manually | Go $10/month and Go Plus $40/month, monthly dollar limit per model split into 5-hour and weekly windows |
| Free models | Usage needs a plan or wallet balance | 12 limited-time free models listed; free quota of 200 requests/day |
| Spend limits | Monthly spend cap and model allow-list per key; alerts at 50/75/90/100% | Monthly limits per workspace and per member, model allow/deny per workspace; auto-reload can exceed the limit |
| Data handling | Prompts and responses are not stored by Tokens; the upstream provider's policy applies | Models hosted in the US; providers follow zero retention, with listed exceptions (some free models; OpenAI and Anthropic keep 30 days) |
Choose Tokens when
- Pay locally with a BDT invoice instead of a USD card.
- One base URL per API format for every model, so moving from DeepSeek to Claude is a model change rather than an endpoint change.
- Per-key spend caps and model allow-lists are useful for CI jobs and shared scripts.
- The same setup command also configures Claude Code, Codex CLI and Crush, not only OpenCode.
Choose OpenCode Zen when
- Zen is built into OpenCode; Tokens needs a custom provider entry (the CLI writes it, but it is one more step).
- No free models; Zen lists several limited-time free ones.
- Zen passes provider cost through; Tokens sets its own per-model prices, so compare on /models before switching.
Switch your client
Point the client at Tokens and swap the key. Your code and agent setup stay the same.
bash
# OpenCode: add a "tokens" provider next to Zen (opencode.json is backed up first) curl -fsSL https://tokens.bd/cli/tokens.mjs -o tokens.mjs node tokens.mjs setup --base-url https://tokens.bd --agents opencode # Zen ids look like opencode/<model-id>; Tokens ids look like tokens/<provider>/<model>, # e.g. tokens/deepseek/deepseek-v4.1-flash (list yours with: node tokens.mjs models) # Other agents: replace the Zen base URL (https://opencode.ai/zen/v1) export TOKENS_API_KEY=tok_live_your_key export OPENAI_BASE_URL=https://tokens.bd/v1 export OPENAI_API_KEY=$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 vsMoonshot Kimi APIMoonshot 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.
- 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 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.