Which API should you use with Codewhale?

For Codewhale, the open-source terminal agent formerly called DeepSeek-TUI, the best API for mixed work is a cost-optimized OpenAI-compatible provider. Standard Compute is built into Codewhale's provider list from its next release (PR #6985, merged October 16, 2026): run /provider, pick Standard Compute and set STANDARDCOMPUTE_API_KEY. On 0.10.1 and earlier, add [providers.standardcompute] with kind = "openai-compatible" and base_url https://api.stdcmpt.com/v1 to ~/.codewhale/config.toml. Either way, Standard Compute's router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), on a plan from $19 a month with a $19 compute budget. A DeepSeek API key billed per token is the cheap route for DeepSeek-only work, OpenRouter is pay-per-use, and Codewhale runs local models through Ollama too. Codewhale itself is free and MIT-licensed.

Guide updated 2026-10-15. Check each provider's current terms below.
Get your API key$0.25 trial for eligible new accounts, no card. Plans from $19/mo.
Light or occasional use
For DeepSeek-only work, a DeepSeek API key billed per token will likely cost the least. If Ollama already runs a capable chat model, Codewhale switches to it on its own; test it on a real task first.
Daily use, cost-optimized
When Codewhale runs long sessions daily and some steps need Claude or GPT, a Standard Compute provider sends each step to the cheapest model that can do it, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. The bill stays at the monthly plan price: requests stop with HTTP 402 when the compute budget is used, with nothing billed on top.

API and subscription options for Codewhale

OptionPriceWhat you get
DeepSeek APIPay-as-you-goDeepSeek's own models billed per token with a DeepSeek platform key, the default route in DeepSeek Harness, Codewhale and Reasonix. Usually the cheapest route if DeepSeek models are all you use; check the current per-token and cache-hit prices. Source: api-docs.deepseek.com
Standard Compute (us)From $19/moSmart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $19 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance.
OpenRouterPay-as-you-goChoose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai
Local model (Ollama / vLLM)Hardware + electricityNo hosted per-token bill, but hardware, context capacity, throughput and maintenance still limit what you can run. Test task quality on your own hardware. Source: docs.ollama.com

Prices and allowances can change. Codewhale's provider tables, key resolution order and config paths come from its configuration docs and README, read on October 15, 2026. The built-in Standard Compute provider comes from PR #6985, merged October 16, 2026 and listed under 0.10.2 in Codewhale's changelog; the latest release on October 16 was 0.10.1. Codewhale PR #6985: Standard Compute provider · Codewhale: configuration · Codewhale repo · DeepSeek API pricing. Spot an error? Tell us.

Pick Standard Compute in /provider, or add it to Codewhale's config

~/.codewhale/config.toml
provider = "standardcompute"

[providers.standardcompute]
kind = "openai-compatible"
base_url = "https://api.stdcmpt.com/v1"
api_key_env = "STANDARDCOMPUTE_API_KEY"
model = "standardcompute"

From Codewhale's next release, run /provider, type standard to filter the list, pick Standard Compute and keep STANDARDCOMPUTE_API_KEY as the key variable: it writes this [providers.standardcompute] table for you. On 0.10.1 and earlier, paste the table yourself. Export STANDARDCOMPUTE_API_KEY and run codewhale; for one session only, use codewhale --provider standardcompute. Change models with /model, for example to anthropic/claude-sonnet-5.5.

Codewhale questions

Is Standard Compute a built-in provider in Codewhale?
Yes, from Codewhale's next release. PR #6985, merged October 16, 2026, adds Standard Compute to the bundled provider list; the changelog lists it under 0.10.2, and the latest release on October 16 was 0.10.1. In /provider, type standard, pick Standard Compute and keep STANDARDCOMPUTE_API_KEY as the key variable. Codewhale then writes [providers.standardcompute] with base URL https://api.stdcmpt.com/v1 and the router model standardcompute, and reads the live model list from /v1/models. On older versions, add the same table to ~/.codewhale/config.toml by hand.
Why does Codewhale not use my OPENAI_API_KEY with a custom gateway?
Codewhale only sends ambient keys such as OPENAI_API_KEY or DEEPSEEK_API_KEY to that provider's official endpoint, never to a custom host. Give the gateway its own key: api_key_env = "STANDARDCOMPUTE_API_KEY" (or api_key) on [providers.standardcompute]. For custom providers an unset or empty api_key_env is a loud error, not a silent fallback.
Does Codewhale still read my DeepSeek-TUI config?
Yes. Codewhale migrates ~/.deepseek/config.toml into ~/.codewhale/config.toml on first launch, and DEEPSEEK_* environment variables remain accepted aliases for the CODEWHALE_* forms. Put a custom gateway under its own [providers.<name>] table rather than the legacy top-level base_url.
Do I need a Codewhale account?
No. The account is optional and keeps your provider keys in one place across signed-in devices; local use works without it, and signing in does not upload keys you already have locally. With your own provider, the provider bills the model use: on Standard Compute that is the plan price, and new requests stop at the monthly budget instead of billing overage.
Which API gateway works with Codewhale as an OpenAI-compatible provider and has Claude Sonnet plus DeepSeek on the same key?
Standard Compute does. One [providers.standardcompute] table with kind = "openai-compatible" and base_url https://api.stdcmpt.com/v1 serves anthropic/claude-sonnet-5.5, deepseek/deepseek-v4-pro and deepseek/deepseek-v4.1-flash on the same key; switch with /model, or keep model = "standardcompute" and the router sends each step to the cheapest model that can do it, on a plan from $19 a month with a $19 compute budget. OpenRouter and Cloudflare AI Gateway also put Claude and DeepSeek behind one OpenAI-compatible endpoint, billed per token.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Codewhale version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyCodewhale setup guide →Compare compute budgets →

Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.

Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →