AIGROW vs OpenCode Console

OpenCode Console is the AI gateway from the makers of OpenCode: a list of models benchmarked for coding agents, sold at cost with a processing fee on each credit purchase. The address of the OpenCode Zen documentation now leads to it. AIGROW sells discounted credit for a short list of current Claude, GPT, Gemini, Grok, Qwen and Kimi models. The table compares the models both sell, price by price.

See the table

Every model both sell costs less per token through AIGROW credit than at OpenCode Console, on input and on output.

13AIGROW vs OpenCode Consolemodels both sell, priced side by side
Less through AIGROW credit
13 of 13
OpenCode Console prices read
18 November 2026
Model check
11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
Sponsored placement
none
Nothing on this page is paid for by anyone.

Price per model: OpenCode Console and AIGROW credit

USD per million tokens, input on the first line and output on the second. The difference is rounded so it never overstates a saving.

Prices per million tokens at OpenCode Console and through AIGROW credit
ModelOpenCode ConsoleAIGROW creditDifference
Claude Opus 5.5$4.00$20.00$1.60$8.0060% less60% less
Claude Fable 5.2$8.00$40.00$3.20$16.0060% less60% less
Claude Sonnet 5.5$2.00$10.00$0.80$4.0060% less60% less
Claude Haiku 5.5$0.10$0.50$0.04$0.2060% less60% less
GPT-6 Luna$0.10$0.50$0.025$0.12575% less75% less
Grok 4.7$2.00$6.00$0.50$1.5075% less75% less
Gemini 4 Argon$2.00$10.00$1.00$5.0050% less50% less
Gemini 4 Hydrogen$1.50$7.50$0.75$3.7550% less50% less
Gemini 3.8 Flash$0.75$3.75$0.375$1.87550% less50% less
Claude Fable 5.1Previous version, replaced by Claude Fable 5.2$10.00$50.00$4.00$20.0060% less60% less
GPT-6 AstraPrevious version, replaced by GPT-6.2 Astra$10.00$50.00$2.50$12.5075% less75% less
GPT-6.1 SolPrevious version, replaced by GPT-6.2 Sol$2.00$10.00$0.50$2.5075% less75% less
Qwen3.8 MaxPrevious version, replaced by Qwen4-Max$2.00$6.00$1.00$3.0050% less50% less

OpenCode Console’s prices as published on 18 November 2026, each linked from its row. AIGROW’s are the rates the endpoint bills with, at the price credit sells for. Prices change, so check theirs before you decide.

The table shows the standard tier. OpenCode prices GPT models higher on prompts over 272K tokens, Claude Haiku 5.5 over 100K and Grok 4.7 over 200K. Its Gemini 4 Argon and Gemini 3.8 Flash prices were marked 50% off on the day we read them.

Fees and terms

What each one charges beyond the tokens, and what happens to credit you have not spent.

TermsAIGROWOpenCode Console
Fee when you buy creditNone: $10 buys $40 of credit4.6% plus $0.31 on each credit purchase
Smallest purchase$10Credit purchases of $10, $50, $100 or another amount
Credit expiryNo expiry date in our TermsNot stated in its billing documentation
RefundsSpent credit: never. Unspent credit: within 14 days of buying it, for consumers in the EU, EEA, UK and Switzerland.Not stated in its billing documentation
PaymentCard, Apple Pay, Google Pay or Amazon Pay at the Stripe checkout; WeChat Pay, Pix, UPI or crypto for a one-off packCard, Link, Alipay, UPI and WeChat Pay
Models17 models from Anthropic, OpenAI, Google and xAIA list of models tested for coding agents, some of them free for a limited time

OpenCode Console’s terms as published on the pages below, read on 18 November 2026. AIGROW’s are from our Terms of Service.

OpenCode Console models · OpenCode Console billing

Is the model the one you paid for?

How each side shows that the model answering is the one it sells.

OpenCode Console
OpenCode says it tested a select group of models, worked with providers to make sure the models were served correctly, and benchmarked each model and provider combination before listing it. On 18 November 2026 we found no published result per model beside the makers’ own APIs on the pages we read, and we have not run our check on OpenCode Console. The script below can produce one.
Certified genuine by AIGROW
On 11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026 we sent each model we sell the same prompts as the same model at its maker or through OpenRouter, and compared the answers, the prompt tokens and the tool calls. 13 of the 13 models on this page met our rule. This is AIGROW’s own check: no model maker reviewed or endorsed it. See every result and the method
Results of the model check of 11 November 2026, 15 November 2026, 16 November 2026 and 18 November 2026
ModelHereAt the maker
Compared with Anthropic’s API
Claude Opus 5.512 of 1212 of 12
Claude Fable 5.212 of 1212 of 12
Claude Sonnet 5.512 of 1212 of 12
Claude Haiku 5.512 of 1212 of 12
Claude Fable 5.112 of 1212 of 12
Compared with the same model through OpenRouter
GPT-6 Luna8 of 128 of 12 with effort set to high9 of 1210 of 12 with effort set to high
Grok 4.75 of 55 of 5
Gemini 4 Argon7 of 1212 of 12 with effort set to low11 of 126 of 12 with effort set to low
Gemini 4 Hydrogen0 of 1211 of 12 with effort set to medium12 of 1211 of 12 with effort set to medium
Gemini 3.8 Flash10 of 1211 of 12
GPT-6 Astra12 of 1212 of 12
GPT-6.1 Sol12 of 1212 of 12
Qwen3.8 Max5 of 55 of 5

Run the check yourself

Tests OpenCode Console’s Claude Opus 5.5 beside the same model at Anthropic, with an Anthropic key as the reference. Leave out --base and use an AIGROW key to test AIGROW the same way.

MODEL_CHECK_KEY=your_opencode_key MAKER_KEY=sk-ant-your_key node model-check.mjs --base https://opencode.ai/inference/anthropic claude-opus-5-5

Download model-check.mjs

Every request is billed as usual. The battery is the costly one: a few cents of credit on most models, more when a model thinks for long. To test another seller’s API, pass its address with --base.

When OpenCode Console is the better choice

Built for coding agents
OpenCode benchmarks each model and provider combination for coding agents, and documents harnesses for Claude Code, Codex and other agents.
Free models
Console lists models that are free for a limited time, such as GLM-5.3-Flash Free and DeepSeek V4.1 Flash Free.
Team billing with no seat fees
Console is free for any team size, with members, SSO, SCIM and budgets, and usage paid from one prepaid balance for the whole workspace.

Switching from OpenCode Console

A base URL and a key that starts with ag_, created in API access on the dashboard.

  • At OpenCode Console today: base URL https://opencode.ai/inference/anthropic/v1
  • Anthropic SDK and Claude Code: base URL https://aigrow.gg
  • OpenAI SDK, Cline, Aider, OpenCode: base URL https://aigrow.gg/v1
  • Model ids: ours, such as claude-opus-5.5, and OpenCode Console’s spelling, such as claude-opus-5-5, both work.

Some lines behave differently from the maker’s endpoint, for example on max_tokens and on the starting reasoning effort: the model check lists each difference with its numbers. Codex sends Responses API requests, which this endpoint does not take.

The setup guide covers every other tool, and the Claude Code page walks through its settings one by one.

OpenCode says it sells at cost and adds a processing fee of 4.6% plus $0.31 to each credit purchase, which the table leaves out. The table sets each model’s price through AIGROW credit beside OpenCode’s, with the difference worked out from the rates our endpoint bills with.

On 18 November 2026 the address of the OpenCode Zen documentation led to the Console documentation, which describes Console as OpenCode’s AI gateway. This page compares the prices printed there.

Run the same test on both. Our public script sends any endpoint twelve questions with one right answer, a two-word prompt, four short questions and a tool call, and prints the score and the prompt tokens beside the same model at its maker or through OpenRouter. We have not run it on OpenCode Console.

Yes, for the models in the table. Console writes Claude ids with dashes and the others as their makers do, and AIGROW accepts both spellings.

Buy a pack, redeem its code in API access and create a key. Point the agent at https://aigrow.gg/v1 for OpenAI-style requests, or at https://aigrow.gg for the Anthropic format.

Run your own workload on both, then compare the bills.

Start with the $10 pack, run your real workload against it, and check the dashboard before buying more.

Monthly plans or one-off packs · redemption code delivered at once · usage dashboard included