8 measured metrics · 1 study
Together AIvsBaseten
No row separates them: 2 ties, 6 unclear.
The verdict
Together AI and Baseten share 8 reported list prices from one study. No row names a winner: a reported list price has no interval, so each gap is stated, not ranked. Prices change often; the snapshot date is in each row’s context. The rows are 2 ties and 6 unclear; each row says why.
Headline metrics
How far apart the two sides are on the headline metrics. Length is the ratio of the two values; it is not a winner.
Bar length is the ratio of the two values on a log scale, pointing to the larger one. Larger is not better for time, tokens or cost. A bar has a side’s color only when that side is ahead in the data; gray means the data does not separate them.
| Metric | Together AI | Baseten | n | Interval or range | Outcome | Basis | Study |
|---|---|---|---|---|---|---|---|
| gpt-oss-120b: price per million tokens by provider (Input) | $0.15gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.10fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.15 vs $0.10, 1.5x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| gpt-oss-120b: price per million tokens by provider (Output) | $0.60gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.50fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.60 vs $0.50, 1.2x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Input) | $2.70Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $3.00fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($2.70 vs $3.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Output) | $13.50Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $15.00fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($13.50 vs $15.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Cache read) | $0.27Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.30fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.27 vs $0.30, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| GLM 5.3: price per million tokens by provider (Input) | $1.40GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $1.40fp4 · GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Tie | Same reported list price. | Inference provider index: 27 models, 52 providers |
n is shown per side on every row
6 headline metrics as the ratio of the two values. None of them separates the sides in the data. Widest ratio: gpt-oss-120b: price per million tokens by provider (Input), 1.5x (Together AI larger).
Metric by metric
Both values of a row come from the same chart in the same study. Each row has its own axis. The shaded band is where the two intervals or ranges overlap: a side is ahead only when they do not.
- Together AI
- Baseten
- where the two overlap
Inference provider index: 27 models, 52 providers
- gpt-oss-120b: price per million tokens by provider (Input)$0.15$0.10Uncleargpt-oss-120b: price per million tokens by provider (Input): Together AI $0.15; Baseten $0.10. Unclear.
- gpt-oss-120b: price per million tokens by provider (Output)$0.60$0.50Uncleargpt-oss-120b: price per million tokens by provider (Output): Together AI $0.60; Baseten $0.50. Unclear.
- Kimi K3: price per million tokens by provider (Input)$2.70$3.00UnclearKimi K3: price per million tokens by provider (Input): Together AI $2.70; Baseten $3.00. Unclear.
- Kimi K3: price per million tokens by provider (Output)$13.50$15.00UnclearKimi K3: price per million tokens by provider (Output): Together AI $13.50; Baseten $15.00. Unclear.
- Kimi K3: price per million tokens by provider (Cache read)$0.27$0.30UnclearKimi K3: price per million tokens by provider (Cache read): Together AI $0.27; Baseten $0.30. Unclear.
- GLM 5.3: price per million tokens by provider (Input)$1.40$1.40TieGLM 5.3: price per million tokens by provider (Input): Together AI $1.40; Baseten $1.40. Tie.
- GLM 5.3: price per million tokens by provider (Output)$4.40$4.40TieGLM 5.3: price per million tokens by provider (Output): Together AI $4.40; Baseten $4.40. Tie.
- GLM 5.3: price per million tokens by provider (Cache read)$0.26$0.14UnclearGLM 5.3: price per million tokens by provider (Cache read): Together AI $0.26; Baseten $0.14. Unclear.
| Metric | Together AI | Baseten | n | Interval or range | Outcome | Basis | Study |
|---|---|---|---|---|---|---|---|
| gpt-oss-120b: price per million tokens by provider (Input) | $0.15gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.10fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.15 vs $0.10, 1.5x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| gpt-oss-120b: price per million tokens by provider (Output) | $0.60gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.50fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.60 vs $0.50, 1.2x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Input) | $2.70Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $3.00fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($2.70 vs $3.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Output) | $13.50Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $15.00fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($13.50 vs $15.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| Kimi K3: price per million tokens by provider (Cache read) | $0.27Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.30fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.27 vs $0.30, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
| GLM 5.3: price per million tokens by provider (Input) | $1.40GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $1.40fp4 · GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Tie | Same reported list price. | Inference provider index: 27 models, 52 providers |
| GLM 5.3: price per million tokens by provider (Output) | $4.40GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $4.40fp4 · GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Tie | Same reported list price. | Inference provider index: 27 models, 52 providers |
| GLM 5.3: price per million tokens by provider (Cache read) | $0.26GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | $0.14fp4 · GLM 5.3 · reported by OpenRouter’s public API, snapshot 2026-10-06 | — | none recorded | Unclear | A reported list price has no interval, so the gap ($0.26 vs $0.14, 1.9x) is stated, not ranked. Check quantization and context before treating the two as equal products. | Inference provider index: 27 models, 52 providers |
n is shown per side on every row
8 rows from 1 study. No row separates them: 2 ties, 6 unclear.
When to pick which
Only from the rows above. A tie is not a reason to pick either side.
When to pick Together AI
No row in this data puts Together AI ahead of Baseten. Pick on other grounds (price, access, the tasks you run), or measure your own workload.
When to pick Baseten
No row in this data puts Baseten ahead of Together AI. Pick on other grounds (price, access, the tasks you run), or measure your own workload.
Side by side
The study charts, showing only these two. Open a study for every configuration.
Input
Output
Cache read
One panel per series, all on the same axis.
| Item | Input | Output | Cache read |
|---|---|---|---|
| BaseTen (fp4) | $0.1 | $0.5 | $0.1 |
| Together | $0.15 | $0.6 | — |
Third-party reported values. 2 rows, 3 series: Input, Output, Cache read. Input: highest Together $0.15. Lowest BaseTen (fp4) $0.1. Output: highest Together $0.6. Lowest BaseTen (fp4) $0.5.
Notes
Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06
Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.
Source: OpenRouter public API: models and provider endpoints (snapshot)
Input
Output
Cache read
One panel per series, all on the same axis.
| Item | Input | Output | Cache read |
|---|---|---|---|
| Together | $2.70 | $13.50 | $0.27 |
| BaseTen (fp8) | $3.00 | $15.00 | $0.3 |
Third-party reported values. 2 rows, 3 series: Input, Output, Cache read. Input: highest BaseTen (fp8) $3.00. Lowest Together $2.70. Output: highest BaseTen (fp8) $15.00. Lowest Together $13.50.
Notes
Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06
Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.
Source: OpenRouter public API: models and provider endpoints (snapshot)
Input
Output
Cache read
One panel per series, all on the same axis.
| Item | Input | Output | Cache read |
|---|---|---|---|
| BaseTen (fp4) | $1.40 | $4.40 | $0.14 |
| Together | $1.40 | $4.40 | $0.26 |
Third-party reported values. 2 rows, 3 series: Input, Output, Cache read. Input: all at $1.40. Output: all at $4.40.
Notes
Standard tier, one bar per provider (its cheapest standard endpoint); reported by OpenRouter’s public API, snapshot 2026-10-06
Prices reported by OpenRouter’s public API, snapshot 2026-10-06; third-party-reported, not measured by Agent. Sorted from the lowest to the highest blended price (3 input : 1 output). A parenthesis names the quantization the provider reported; lower precision or a shorter context can explain a lower price, so check the endpoint table. Flex, priority, fast and regional endpoints are left out here because they are priced differently on purpose.
Source: OpenRouter public API: models and provider endpoints (snapshot)
How a row is called
- AheadThe 95% intervals do not overlap, or the run ranges or p50–p95 bands do not overlap with at least 5 runs per side.
- TieThe values match, or both sit at the same ceiling.
- UnclearThe intervals or ranges overlap, too few runs were recorded, no interval was recorded, or more is not better (token counts are never a win).
- CalculationDerived from list prices and recorded counts. Not a bill and not a run.
The dataset compiler makes every call; this page only draws it. No composite score, no rank.
Questions
- Which is better, Together AI or Baseten?
- Together AI and Baseten share 8 reported list prices from one study. No row names a winner: a reported list price has no interval, so each gap is stated, not ranked. Prices change often; the snapshot date is in each row’s context. The rows are 2 ties and 6 unclear; each row says why.
- How were Together AI and Baseten measured?
- They share 8 measured metrics from 1 public study: Inference provider index: 27 models, 52 providers. Every row names its configuration, its sample size and its interval or range.
- How do Together AI and Baseten compare on gpt-oss-120b: price per million tokens by provider (Input)?
- Together AI: $0.15 (gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06). Baseten: $0.10 (fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06). A reported list price has no interval, so the gap ($0.15 vs $0.10, 1.5x) is stated, not ranked. Check quantization and context before treating the two as equal products.
- How do Together AI and Baseten compare on gpt-oss-120b: price per million tokens by provider (Output)?
- Together AI: $0.60 (gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06). Baseten: $0.50 (fp4 · gpt-oss-120b · reported by OpenRouter’s public API, snapshot 2026-10-06). A reported list price has no interval, so the gap ($0.60 vs $0.50, 1.2x) is stated, not ranked. Check quantization and context before treating the two as equal products.
- How do Together AI and Baseten compare on kimi K3: price per million tokens by provider (Input)?
- Together AI: $2.70 (Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). Baseten: $3.00 (fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). A reported list price has no interval, so the gap ($2.70 vs $3.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products.
- How do Together AI and Baseten compare on kimi K3: price per million tokens by provider (Output)?
- Together AI: $13.50 (Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). Baseten: $15.00 (fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). A reported list price has no interval, so the gap ($13.50 vs $15.00, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products.
- How do Together AI and Baseten compare on kimi K3: price per million tokens by provider (Cache read)?
- Together AI: $0.27 (Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). Baseten: $0.30 (fp8 · Kimi K3 · reported by OpenRouter’s public API, snapshot 2026-10-06). A reported list price has no interval, so the gap ($0.27 vs $0.30, 1.1x) is stated, not ranked. Check quantization and context before treating the two as equal products.
The studies behind this page
Inference provider index: 27 models, 52 providers
Price per million tokens for 27 models across 52 providers, the spread between them and OpenRouter’s markup over first-party prices.