OG 5.4
webparam/og-5-4-standardStandard tier — general-purpose work at a middle price.
Model overview
Input price
R40.00
per 1M tokens
Output price
R150.00
per 1M tokens
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
4
of 11 tags
Description
OG 5.4 is a language model from Webparam. It generates language output and is priced at R40.00 per 1M tokens in and R150.00 per 1M tokens out. That places its input price above the language-category median of R29.10. Webparam’s stated focus is one account, one wallet, one API key — billed in rand. The weights are not published, so it is API-only.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Reasoning
- Spends extra billed tokens thinking before it answers, trading latency and cost for accuracy.
Strengths & weaknesses
Strengths
- Quick to respond — 1.7s to first token
- Tool calling and JSON mode both verified working
- Returned content on 5 of 5 requests in reliability testing
Weaknesses
- About 21% of billed output tokens are internal reasoning you never see
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | R40.00 | per 1M tokens |
| Output | R150.00 | per 1M tokens |
Rates are what Webparam charges, in rand.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Not supported |
| Reasoning | Supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
General assistants
Retrieval-augmented answering
Everyday production traffic
Comparison
Compare against anything →| Attribute | OG 5.4 | OG 5.5 | OG 5.6 Sol |
|---|---|---|---|
| Input price | R40.00 | R40.00 | R40.00 |
| Output price | R150.00 | R150.00 | R150.00 |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Supported | Supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Not supported | Not supported | Not supported |
| Prompt caching | Not supported | Not supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
OG 5.4 runs on GPT-5.4, which AWS Bedrock and Microsoft Foundry also sell. See what they charge for it.
Provider information
View Webparam →Webparam · Johannesburg, South Africa, South Africa · est. 2026
Webparam aggregates frontier model capacity and resells it through a single OpenAI-compatible endpoint, so a company can reach the models it needs without holding an account, a card and a contract with each vendor.
Recent releases
Documentation
Frequently asked questions
Input is billed at R40.00 per 1M tokens and output at R150.00 per 1M tokens. Every figure on this page is an illustrative placeholder.
No. OG 5.4 is served through its provider's API only; the weights are not published, so self-hosting is not an option.
OG 5.5 is the closest neighbour in the catalogue, with — of context at R40.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.