Tokens vs OpenAI API
OpenAI'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.
Buying from OpenAI directly gives you GPT-6 Luna at $0.10 / $0.50 per million tokens for prompts up to 272K tokens, Batch and Flex processing at half that, Fast mode when latency matters, and OpenAI-only APIs for images, audio, realtime, files and fine-tuning. You pay with prepaid credits by credit or debit card in USD; OpenAI's help center says the minimum purchase is $5 and purchased credits expire after one year. Tokens supports Chat Completions and the Responses API at https://tokens.bd/v1, so the OpenAI SDK and Codex CLI work after a base-URL change, and the same key reaches Claude, Gemini, DeepSeek, Kimi and others. It does not cover images, audio, files, batches or fine-tuning. Go direct for those features or the Batch discount. Use Tokens to pay in BDT and keep several providers under one bill.
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
OpenAI API
- Pricing model
- Prepaid USD credits, per token; Batch and Flex 50% off, Fast mode 2x; higher rates above 272K input tokens
- Payment methods
- Credit or debit card in USD (prepaid cards not accepted)
- Prices checked
- 3 Oct 2026
- GPT-6 Luna, over 272K (per 1M tokens, in / out)
- $0.20 / $0.75
- GPT-6 Luna, up to 272K (per 1M tokens, in / out)
- $0.10 / $0.50
- GPT-5.6 Luna, up to 272K (per 1M tokens, in / out)
- $0.20 / $1.20
- GPT-6 Luna Batch, up to 272K (per 1M tokens, in / out)
- $0.05 / $0.25
- GPT-5.6 Sol, promo until at least 21 Nov 2026 (per 1M tokens, in / out)
- $4.00 / $20.00
Side by side
A tick marks the better option for that row. Some rows go to the other side.
| Topic | Tokens | OpenAI API |
|---|---|---|
| Price | Set per model by Tokens; see /models | OpenAI's list price |
| Batch and Flex | Not supported | Batch and Flex processing at 50% off |
| Endpoint coverage | Chat Completions, legacy Completions, Responses and Models, plus Anthropic Messages | Also images, audio, realtime, files, fine-tuning and moderations |
| Paying from Bangladesh | BDT invoice through the billing portal | Card in USD, prepaid cards refused. Bangladesh Bank FE Circular 26 (2019) limits international-card online payments to USD 300 per transaction |
| Providers on one key | GPT plus Claude, Gemini, Grok, DeepSeek, Kimi, GLM, Qwen and others | OpenAI models only |
| Codex CLI setup | The setup CLI writes a [model_providers.tokens] profile; run codex --profile tokens | Works by default with an OpenAI key |
| Network path | One extra gateway hop | Direct to the model maker |
Choose Tokens when
- Pay a BDT invoice instead of buying USD credits with an international card.
- One key for GPT and for Claude, Gemini, DeepSeek or Kimi, in OpenAI or Anthropic format.
- Per-key monthly spend caps and model allow-lists, with usage alerts at 50, 75, 90 and 100%.
- One command sets up Codex CLI, Claude Code, OpenCode and Crush.
Choose OpenAI API when
- OpenAI's list price is the floor, and Batch or Flex halves it; Tokens has neither.
- No images, audio, realtime, files or fine-tuning through Tokens.
- Adds a gateway hop and one more party in the data path (Tokens does not store prompt or response content).
Switch your client
Point the client at Tokens and swap the key. Your code and agent setup stay the same.
bash
# OpenAI SDKs read these variables; the default base URL was https://api.openai.com/v1 export TOKENS_API_KEY=tok_live_your_key export OPENAI_BASE_URL=https://tokens.bd/v1 export OPENAI_API_KEY=$TOKENS_API_KEY # Model ids gain a provider prefix; list the ones your key can call curl -s https://tokens.bd/v1/models -H "Authorization: Bearer $TOKENS_API_KEY" # Codex CLI: add a "tokens" profile to ~/.codex/config.toml (backed up first) curl -fsSL https://tokens.bd/cli/tokens.mjs -o tokens.mjs node tokens.mjs setup --base-url https://tokens.bd --agents codex codex --profile tokens
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 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.