Traffic rank on Composite
#178 of 196
0% of tokens and 0% of requests over 30 days.
AI model
OpenAI: gpt-oss-20b
openai/gpt-oss-20b
OpenAI: gpt-oss-20b is a 131,072-token model served on Composite at $0.0225 per million tokens in and $0.112 per million tokens out. Ranked #178 of 196 models by traffic on Composite over the last 30 days, taking 0% of tokens and 0% of requests. Measured on Composite, 100.0% of its last 2 requests on Composite succeeded, the typical first token arrives in 634 ms, output runs at about 79.7 tokens per second.
Try in PlaygroundSpecifications
| Model ID | openai/gpt-oss-20b |
|---|---|
| Provider | cv11 |
| Context window | 131,072 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.0225 per million tokens |
| Output price | $0.112 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | About 0.2 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Success rate
100.0%
Across the last 2 requests Composite served for this model.
Time to first token
634 ms
Median across the same sample.
Output speed
79.7 tok/s
Median generation rate after the first token.
Routing variants
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | openai/gpt-oss-20b-normal |
cv11 | $0.0225 per million tokens input · $0.112 per million tokens output |
| Normal + cheapThink | openai/gpt-oss-20b-normal:cheapThink |
cv11 | $0.0225 per million tokens input · $0.112 per million tokens output |
| Cheapest provider | openai/gpt-oss-20b:cheapest-provider |
Darkbloom | $0.0225 per million tokens input · $0.112 per million tokens output |
| Cheapest provider + cheapThink | openai/gpt-oss-20b:cheapest-provider:cheapThink |
Darkbloom | $0.0225 per million tokens input · $0.112 per million tokens output |
| cheapThink | openai/gpt-oss-20b:cheapThink |
cv11 | $0.0225 per million tokens input · $0.112 per million tokens output |
| Fast | openai/gpt-oss-20b:fast |
Darkbloom | $0.0225 per million tokens input · $0.112 per million tokens output |
| Fast + cheapThink | openai/gpt-oss-20b:fast:cheapThink |
Darkbloom | $0.0225 per million tokens input · $0.112 per million tokens output |
| Quality | openai/gpt-oss-20b:quality |
DekaLLM | $0.0363 per million tokens input · $0.175 per million tokens output |
| Quality + cheapThink | openai/gpt-oss-20b:quality:cheapThink |
DekaLLM | $0.0363 per million tokens input · $0.175 per million tokens output |
Pricing
$0.0225 per million tokens input · $0.112 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 0.2 plan credits, at the provider's own price.
Provider
cv11
Roleplay fit
This is an OpenAI model, a dependable baseline with broad instruction-following and consistent formatting across long conversations.
Context behavior
With a 131,072-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
Cost for regular use
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
From the provider
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Supplied by cv11, not written by Composite.
Related models
Composite GPT Router · OpenAI: GPT-6.1 Sol Pro · OpenAI: GPT-6.1 Sol